Show of Hands:Votes: Party classification:: Q109244No_category_cnk01_rest
bdanalytics
Date: (Sat) Jun 11, 2016
Introduction:
Data: Source: Training: “https://inclass.kaggle.com/c/can-we-predict-voting-outcomes/download/train2016.csv”
New: “https://inclass.kaggle.com/c/can-we-predict-voting-outcomes/download/test2016.csv”
Time period:
Synopsis:
Based on analysis utilizing <> techniques,
Summary of key steps & error improvement stats:
Prediction Accuracy Enhancement Options:
- transform.data chunk:
- derive features from multiple features
- manage.missing.data chunk:
- Not fill missing vars
- Fill missing numerics with a different algorithm
- Fill missing chars with data based on clusters
[](.png)
Potential next steps include:
- Organization:
- Categorize by chunk
- Priority criteria:
- Ease of change
- Impacts report
- Cleans innards
- Bug report
- all chunks:
- at chunk-end rm(!glb_)
- manage.missing.data chunk:
- cleaner way to manage re-splitting of training vs. new entity
- extract.features chunk:
- Add n-grams for glbFeatsText
- “RTextTools”, “tau”, “RWeka”, and “textcat” packages
- Add n-grams for glbFeatsText
- fit.models chunk:
- Classification: Plot AUC Curves for all models & highlight glbMdlSel
- Prediction accuracy scatter graph:
- Add tiles (raw vs. PCA)
- Use shiny for drop-down of “important” features
Use plot.ly for interactive plots ?
- Change .fit suffix of model metrics to .mdl if it’s data independent (e.g. AIC, Adj.R.Squared - is it truly data independent ?, etc.)
- create a custom model for rpart that has minbucket as a tuning parameter
varImp for randomForest crashes in caret version:6.0.41 -> submit bug report
- Probability handling for multinomials vs. desired binomial outcome
- ROCR currently supports only evaluation of binary classification tasks (version 1.0.7)
extensions toward multiclass classification are scheduled for the next release
- fit.all.training chunk:
- myplot_prediction_classification: displays ‘x’ instead of ‘+’ when there are no prediction errors
- Compare glb_sel_mdl vs. glb_fin_mdl:
- varImp
- Prediction differences (shd be minimal ?)
- Move glb_analytics_diag_plots to mydsutils.R: (+) Easier to debug (-) Too many glb vars used
- Add print(ggplot.petrinet(glb_analytics_pn) + coord_flip()) at the end of every major chunk
- Parameterize glb_analytics_pn
- Move glb_impute_missing_data to mydsutils.R: (-) Too many glb vars used; glb_<>_df reassigned
- Do non-glm methods handle interaction terms ?
- f-score computation for classifiers should be summation across outcomes (not just the desired one ?)
- Add accuracy computation to glb_dmy_mdl in predict.data.new chunk
- Why does splitting fit.data.training.all chunk into separate chunks add an overhead of ~30 secs ? It’s not rbind b/c other chunks have lower elapsed time. Is it the number of plots ?
- Incorporate code chunks in print_sessionInfo
- Test against
- projects in github.com/bdanalytics
- lectures in jhu-datascience track
Analysis:
rm(list = ls())
set.seed(12345)
options(stringsAsFactors = FALSE)
source("~/Dropbox/datascience/R/mycaret.R")
source("~/Dropbox/datascience/R/mypetrinet.R")
source("~/Dropbox/datascience/R/myplclust.R")
source("~/Dropbox/datascience/R/myplot.R")
source("~/Dropbox/datascience/R/myscript.R")
source("~/Dropbox/datascience/R/mytm.R")
if (is.null(knitr::opts_current$get(name = 'label'))) # Running in IDE
debugSource("~/Dropbox/datascience/R/mydsutils.R") else
source("~/Dropbox/datascience/R/mydsutils.R") ## Loading required package: caret## Loading required package: lattice# Gather all package requirements here
suppressPackageStartupMessages(require(doMC))
glbCores <- 10 # of cores on machine - 2
registerDoMC(glbCores)
suppressPackageStartupMessages(require(caret))
require(plyr)## Loading required package: plyrrequire(dplyr)## Loading required package: dplyr##
## Attaching package: 'dplyr'## The following objects are masked from 'package:plyr':
##
## arrange, count, desc, failwith, id, mutate, rename, summarise,
## summarize## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionrequire(knitr)## Loading required package: knitrrequire(stringr)## Loading required package: stringr#source("dbgcaret.R")
#packageVersion("snow")
#require(sos); findFn("cosine", maxPages=2, sortby="MaxScore")
# Analysis control global variables
# Inputs
# url/name = "<PathPointer>"; if url specifies a zip file, name = "<filename>";
# or named collection of <PathPointer>s
# sep = choose from c(NULL, "\t")
glbObsTrnFile <- list(url = "https://inclass.kaggle.com/c/can-we-predict-voting-outcomes/download/train2016.csv"
# or list(url = c(NULL, <.inp1> = "<path1>", <.inp2> = "<path2>"))
#, splitSpecs = list(method = "copy" # default when glbObsNewFile is NULL
# select from c("copy", NULL ???, "condition", "sample", )
# ,nRatio = 0.3 # > 0 && < 1 if method == "sample"
# ,seed = 123 # any integer or glbObsTrnPartitionSeed if method == "sample"
# ,condition = # or 'is.na(<var>)'; '<var> <condition_operator> <value>'
# )
)
glbObsNewFile <- list(url = "https://inclass.kaggle.com/c/can-we-predict-voting-outcomes/download/test2016.csv")
glbObsDropCondition <- #NULL # : default
# enclose in single-quotes b/c condition might include double qoutes
# use | & ; NOT || &&
# '<condition>'
# 'grepl("^First Draft Video:", glbObsAll$Headline)'
# 'is.na(glbObsAll[, glb_rsp_var_raw])'
# '(is.na(glbObsAll[, glb_rsp_var_raw]) & grepl("Train", glbObsAll[, glbFeatsId]))'
# 'is.na(strptime(glbObsAll[, "Date"], glbFeatsDateTime[["Date"]]["format"], tz = glbFeatsDateTime[["Date"]]["timezone"]))'
'(is.na(glbObsAll[, "Q109244"]) | (glbObsAll[, "Q109244"] != "No"))'
#nrow(do.call("subset",list(glbObsAll, parse(text=paste0("!(", glbObsDropCondition, ")")))))
glb_obs_repartition_train_condition <- NULL # : default
# "<condition>"
glb_max_fitobs <- NULL # or any integer
glbObsTrnPartitionSeed <- 123 # or any integer
glb_is_regression <- FALSE; glb_is_classification <- !glb_is_regression;
glb_is_binomial <- TRUE # or TRUE or FALSE
glb_rsp_var_raw <- "Party"
# for classification, the response variable has to be a factor
glb_rsp_var <- "Party.fctr"
# if the response factor is based on numbers/logicals e.g (0/1 OR TRUE/FALSE vs. "A"/"B"),
# or contains spaces (e.g. "Not in Labor Force")
# caret predict(..., type="prob") crashes
glb_map_rsp_raw_to_var <- #NULL
function(raw) {
# return(raw ^ 0.5)
# return(log(raw))
# return(log(1 + raw))
# return(log10(raw))
# return(exp(-raw / 2))
#
# chk ref value against frequencies vs. alpha sort order
ret_vals <- rep_len(NA, length(raw)); ret_vals[!is.na(raw)] <- ifelse(raw[!is.na(raw)] == "Republican", "R", "D"); return(relevel(as.factor(ret_vals), ref = "D"))
# as.factor(paste0("B", raw))
# as.factor(gsub(" ", "\\.", raw))
}
#if glb_rsp_var_raw is numeric:
#print(summary(glbObsAll[, glb_rsp_var_raw]))
#glb_map_rsp_raw_to_var(tst <- c(NA, as.numeric(summary(glbObsAll[, glb_rsp_var_raw]))))
#if glb_rsp_var_raw is character:
#print(table(glbObsAll[, glb_rsp_var_raw], useNA = "ifany"))
# print(table(glb_map_rsp_raw_to_var(tst <- glbObsAll[, glb_rsp_var_raw]), useNA = "ifany"))
glb_map_rsp_var_to_raw <- #NULL
function(var) {
# return(var ^ 2.0)
# return(exp(var))
# return(10 ^ var)
# return(-log(var) * 2)
# as.numeric(var)
# levels(var)[as.numeric(var)]
sapply(levels(var)[as.numeric(var)], function(elm)
if (is.na(elm)) return(elm) else
if (elm == 'R') return("Republican") else
if (elm == 'D') return("Democrat") else
stop("glb_map_rsp_var_to_raw: unexpected value: ", elm)
)
# gsub("\\.", " ", levels(var)[as.numeric(var)])
# c("<=50K", " >50K")[as.numeric(var)]
# c(FALSE, TRUE)[as.numeric(var)]
}
# print(table(glb_map_rsp_var_to_raw(glb_map_rsp_raw_to_var(tst)), useNA = "ifany"))
if ((glb_rsp_var != glb_rsp_var_raw) && is.null(glb_map_rsp_raw_to_var))
stop("glb_map_rsp_raw_to_var function expected")
# List info gathered for various columns
# <col_name>: <description>; <notes>
# USER_ID - an anonymous id unique to a given user
# YOB - the year of birth of the user
# Gender - the gender of the user, either Male or Female
# Income - the household income of the user. Either not provided, or one of "under $25,000", "$25,001 - $50,000", "$50,000 - $74,999", "$75,000 - $100,000", "$100,001 - $150,000", or "over $150,000".
# HouseholdStatus - the household status of the user. Either not provided, or one of "Domestic Partners (no kids)", "Domestic Partners (w/kids)", "Married (no kids)", "Married (w/kids)", "Single (no kids)", or "Single (w/kids)".
# EducationalLevel - the education level of the user. Either not provided, or one of "Current K-12", "High School Diploma", "Current Undergraduate", "Associate's Degree", "Bachelor's Degree", "Master's Degree", or "Doctoral Degree".
# Party - the political party for whom the user intends to vote for. Either "Democrat" or "Republican
# Q124742, Q124122, . . . , Q96024 - 101 different questions that the users were asked on Show of Hands. If the user didn't answer the question, there is a blank. For information about the question text and possible answers, see the file Questions.pdf.
# currently does not handle more than 1 column; consider concatenating multiple columns
# If glbFeatsId == NULL, ".rownames <- as.numeric(row.names())" is the default
glbFeatsId <- "USER_ID" # choose from c(NULL : default, "<id_feat>")
glbFeatsCategory <- "Hhold.fctr" # choose from c(NULL : default, "<category_feat>")
# glbFeatsCategory <- "Q109244.fctr" # choose from c(NULL : default, "<category_feat>") -> OOB performed worse than "Hhold.fctr"
# User-specified exclusions
glbFeatsExclude <- c(NULL
# Feats that shd be excluded due to known causation by prediction variable
# , "<feat1", "<feat2>"
# Feats that are factors with unique values (as % of nObs) > 49 (empirically derived)
# Feats that are linear combinations (alias in glm)
# Feature-engineering phase -> start by excluding all features except id & category &
# work each one in
, "USER_ID", "YOB", "Gender", "Income", "HouseholdStatus", "EducationLevel"
,"Q124742","Q124122"
,"Q123621","Q123464"
,"Q122771","Q122770","Q122769","Q122120"
,"Q121700","Q121699","Q121011"
,"Q120978","Q120650","Q120472","Q120379","Q120194","Q120014","Q120012"
,"Q119851","Q119650","Q119334"
,"Q118892","Q118237","Q118233","Q118232","Q118117"
,"Q117193","Q117186"
,"Q116797","Q116881","Q116953","Q116601","Q116441","Q116448","Q116197"
,"Q115602","Q115777","Q115610","Q115611","Q115899","Q115390","Q115195"
,"Q114961","Q114748","Q114517","Q114386","Q114152"
,"Q113992","Q113583","Q113584","Q113181"
,"Q112478","Q112512","Q112270"
,"Q111848","Q111580","Q111220"
,"Q110740"
,"Q109367","Q109244"
,"Q108950","Q108855","Q108617","Q108856","Q108754","Q108342","Q108343"
,"Q107869","Q107491"
,"Q106993","Q106997","Q106272","Q106388","Q106389","Q106042"
,"Q105840","Q105655"
,"Q104996"
,"Q103293"
,"Q102906","Q102674","Q102687","Q102289","Q102089"
,"Q101162","Q101163","Q101596"
,"Q100689","Q100680","Q100562","Q100010"
,"Q99982"
,"Q99716"
,"Q99581"
,"Q99480"
,"Q98869"
,"Q98578"
,"Q98197"
,"Q98059","Q98078"
,"Q96024" # Done
,".pos")
if (glb_rsp_var_raw != glb_rsp_var)
glbFeatsExclude <- union(glbFeatsExclude, glb_rsp_var_raw)
glbFeatsInteractionOnly <- list()
#glbFeatsInteractionOnly[["<child_feat>"]] <- "<parent_feat>"
glbFeatsInteractionOnly[["YOB.Age.dff"]] <- "YOB.Age.fctr"
glbFeatsDrop <- c(NULL
# , "<feat1>", "<feat2>"
)
glb_map_vars <- NULL # or c("<var1>", "<var2>")
glb_map_urls <- list();
# glb_map_urls[["<var1>"]] <- "<var1.url>"
# Derived features; Use this mechanism to cleanse data ??? Cons: Data duplication ???
glbFeatsDerive <- list();
# glbFeatsDerive[["<feat.my.sfx>"]] <- list(
# mapfn = function(<arg1>, <arg2>) { return(function(<arg1>, <arg2>)) }
# , args = c("<arg1>", "<arg2>"))
#myprint_df(data.frame(ImageId = mapfn(glbObsAll$.src, glbObsAll$.pos)))
#data.frame(ImageId = mapfn(glbObsAll$.src, glbObsAll$.pos))[7045:7055, ]
# character
# mapfn = function(Education) { raw <- Education; raw[is.na(raw)] <- "NA.my"; return(as.factor(raw)) }
# mapfn = function(Week) { return(substr(Week, 1, 10)) }
# mapfn = function(Name) { return(sapply(Name, function(thsName)
# str_sub(unlist(str_split(thsName, ","))[1], 1, 1))) }
# mapfn = function(descriptor) { return(plyr::revalue(descriptor, c(
# "ABANDONED BUILDING" = "OTHER",
# "**" = "**"
# ))) }
# mapfn = function(description) { mod_raw <- description;
# This is here because it does not work if it's in txt_map_filename
# mod_raw <- gsub(paste0(c("\n", "\211", "\235", "\317", "\333"), collapse = "|"), " ", mod_raw)
# Don't parse for "." because of ".com"; use customized gsub for that text
# mod_raw <- gsub("(\\w)(!|\\*|,|-|/)(\\w)", "\\1\\2 \\3", mod_raw);
# Some state acrnoyms need context for separation e.g.
# LA/L.A. could either be "Louisiana" or "LosAngeles"
# modRaw <- gsub("\\bL\\.A\\.( |,|')", "LosAngeles\\1", modRaw);
# OK/O.K. could either be "Oklahoma" or "Okay"
# modRaw <- gsub("\\bACA OK\\b", "ACA OKay", modRaw);
# modRaw <- gsub("\\bNow O\\.K\\.\\b", "Now OKay", modRaw);
# PR/P.R. could either be "PuertoRico" or "Public Relations"
# modRaw <- gsub("\\bP\\.R\\. Campaign", "PublicRelations Campaign", modRaw);
# VA/V.A. could either be "Virginia" or "VeteransAdministration"
# modRaw <- gsub("\\bthe V\\.A\\.\\:", "the VeteranAffairs:", modRaw);
#
# Custom mods
# return(mod_raw) }
# numeric
# Create feature based on record position/id in data
glbFeatsDerive[[".pos"]] <- list(
mapfn = function(raw1) { return(1:length(raw1)) }
, args = c(".rnorm"))
# glbFeatsDerive[[".pos.y"]] <- list(
# mapfn = function(raw1) { return(1:length(raw1)) }
# , args = c(".rnorm"))
# Add logs of numerics that are not distributed normally
# Derive & keep multiple transformations of the same feature, if normality is hard to achieve with just one transformation
# Right skew: logp1; sqrt; ^ 1/3; logp1(logp1); log10; exp(-<feat>/constant)
# glbFeatsDerive[["WordCount.log1p"]] <- list(
# mapfn = function(WordCount) { return(log1p(WordCount)) }
# , args = c("WordCount"))
# glbFeatsDerive[["WordCount.root2"]] <- list(
# mapfn = function(WordCount) { return(WordCount ^ (1/2)) }
# , args = c("WordCount"))
# glbFeatsDerive[["WordCount.nexp"]] <- list(
# mapfn = function(WordCount) { return(exp(-WordCount)) }
# , args = c("WordCount"))
#print(summary(glbObsAll$WordCount))
#print(summary(mapfn(glbObsAll$WordCount)))
# If imputation shd be skipped for this feature
# glbFeatsDerive[["District.fctr"]] <- list(
# mapfn = function(District) {
# raw <- District;
# ret_vals <- rep_len("NA", length(raw));
# ret_vals[!is.na(raw)] <- sapply(raw[!is.na(raw)], function(elm)
# ifelse(elm < 10, "1-9",
# ifelse(elm < 20, "10-19", "20+")));
# return(relevel(as.factor(ret_vals), ref = "NA"))
# }
# , args = c("District"))
# YOB options:
# 1. Missing data:
# 1.1 0 -> Does not improve baseline
# 1.2 Cut factors & "NA" is a level
# 2. Data corrections: < 1928 & > 2000
# 3. Scale YOB
# 4. Add Age
# YOB.Age.fctr needs to be synced with YOB.Age.dff; Create a separate sub-function ???
glbFeatsDerive[["YOB.Age.fctr"]] <- list(
mapfn = function(raw1) {
raw <- 2016 - raw1
# raw[!is.na(raw) & raw >= 2010] <- NA
raw[!is.na(raw) & (raw <= 15)] <- NA
raw[!is.na(raw) & (raw >= 90)] <- NA
retVal <- rep_len("NA", length(raw))
# breaks = c(1879, seq(1949, 1989, 10), 2049)
# cutVal <- cut(raw[!is.na(raw)], breaks = breaks,
# labels = as.character(breaks + 1)[1:(length(breaks) - 1)])
cutVal <- cut(raw[!is.na(raw)], breaks = c(15, 20, 25, 30, 35, 40, 50, 65, 90))
retVal[!is.na(raw)] <- levels(cutVal)[cutVal]
return(factor(retVal, levels = c("NA"
,"(15,20]","(20,25]","(25,30]","(30,35]","(35,40]","(40,50]","(50,65]","(65,90]"),
ordered = TRUE))
}
, args = c("YOB"))
# YOB.Age.fctr needs to be synced with YOB.Age.dff; Create a separate sub-function ???
glbFeatsDerive[["YOB.Age.dff"]] <- list(
mapfn = function(raw1) {
raw <- 2016 - raw1
raw[!is.na(raw) & (raw <= 15)] <- NA
raw[!is.na(raw) & (raw >= 90)] <- NA
breaks <- c(15, 20, 25, 30, 35, 40, 50, 65, 90)
# retVal <- rep_len(0, length(raw))
stopifnot(sum(!is.na(raw) && (raw <= 15)) == 0)
stopifnot(sum(!is.na(raw) && (raw >= 90)) == 0)
# msk <- !is.na(raw) && (raw > 15) && (raw <= 20); if (sum(msk > 0)) retVal[msk] <- raw[msk] - 15
# msk <- !is.na(raw) && (raw > 20) && (raw <= 25); if (sum(msk > 0)) retVal[msk] <- raw[msk] - 20
# msk <- !is.na(raw) && (raw > 25) && (raw <= 30); if (sum(msk > 0)) retVal[msk] <- raw[msk] - 25
# msk <- !is.na(raw) && (raw > 30) && (raw <= 35); if (sum(msk > 0)) retVal[msk] <- raw[msk] - 30
# msk <- !is.na(raw) && (raw > 35) && (raw <= 40); if (sum(msk > 0)) retVal[msk] <- raw[msk] - 35
# msk <- !is.na(raw) && (raw > 40) && (raw <= 50); if (sum(msk > 0)) retVal[msk] <- raw[msk] - 40
# msk <- !is.na(raw) && (raw > 50) && (raw <= 65); if (sum(msk > 0)) retVal[msk] <- raw[msk] - 50
# msk <- !is.na(raw) && (raw > 65) && (raw <= 90); if (sum(msk > 0)) retVal[msk] <- raw[msk] - 65
breaks <- c(15, 20, 25, 30, 35, 40, 50, 65, 90)
retVal <- sapply(raw, function(age) {
if (is.na(age)) return(0) else
if ((age > 15) && (age <= 20)) return(age - 15) else
if ((age > 20) && (age <= 25)) return(age - 20) else
if ((age > 25) && (age <= 30)) return(age - 25) else
if ((age > 30) && (age <= 35)) return(age - 30) else
if ((age > 35) && (age <= 40)) return(age - 35) else
if ((age > 40) && (age <= 50)) return(age - 40) else
if ((age > 50) && (age <= 65)) return(age - 50) else
if ((age > 65) && (age <= 90)) return(age - 65)
})
return(retVal)
}
, args = c("YOB"))
glbFeatsDerive[["Gender.fctr"]] <- list(
mapfn = function(raw1) {
raw <- raw1
raw[raw %in% ""] <- "N"
raw <- gsub("Male" , "M", raw, fixed = TRUE)
raw <- gsub("Female", "F", raw, fixed = TRUE)
return(relevel(as.factor(raw), ref = "N"))
}
, args = c("Gender"))
glbFeatsDerive[["Income.fctr"]] <- list(
mapfn = function(raw1) { raw <- raw1;
raw[raw %in% ""] <- "N"
raw <- gsub("under $25,000" , "<25K" , raw, fixed = TRUE)
raw <- gsub("$25,001 - $50,000" , "25-50K" , raw, fixed = TRUE)
raw <- gsub("$50,000 - $74,999" , "50-75K" , raw, fixed = TRUE)
raw <- gsub("$75,000 - $100,000" , "75-100K" , raw, fixed = TRUE)
raw <- gsub("$100,001 - $150,000", "100-150K", raw, fixed = TRUE)
raw <- gsub("over $150,000" , ">150K" , raw, fixed = TRUE)
return(factor(raw, levels = c("N","<25K","25-50K","50-75K","75-100K","100-150K",">150K"),
ordered = TRUE))
}
, args = c("Income"))
glbFeatsDerive[["Hhold.fctr"]] <- list(
mapfn = function(raw1) { raw <- raw1;
raw[raw %in% ""] <- "N"
raw <- gsub("Domestic Partners (no kids)", "PKn", raw, fixed = TRUE)
raw <- gsub("Domestic Partners (w/kids)" , "PKy", raw, fixed = TRUE)
raw <- gsub("Married (no kids)" , "MKn", raw, fixed = TRUE)
raw <- gsub("Married (w/kids)" , "MKy", raw, fixed = TRUE)
raw <- gsub("Single (no kids)" , "SKn", raw, fixed = TRUE)
raw <- gsub("Single (w/kids)" , "SKy", raw, fixed = TRUE)
return(relevel(as.factor(raw), ref = "N"))
}
, args = c("HouseholdStatus"))
glbFeatsDerive[["Edn.fctr"]] <- list(
mapfn = function(raw1) { raw <- raw1;
raw[raw %in% ""] <- "N"
raw <- gsub("Current K-12" , "K12", raw, fixed = TRUE)
raw <- gsub("High School Diploma" , "HSD", raw, fixed = TRUE)
raw <- gsub("Current Undergraduate", "CCg", raw, fixed = TRUE)
raw <- gsub("Associate's Degree" , "Ast", raw, fixed = TRUE)
raw <- gsub("Bachelor's Degree" , "Bcr", raw, fixed = TRUE)
raw <- gsub("Master's Degree" , "Msr", raw, fixed = TRUE)
raw <- gsub("Doctoral Degree" , "PhD", raw, fixed = TRUE)
return(factor(raw, levels = c("N","K12","HSD","CCg","Ast","Bcr","Msr","PhD"),
ordered = TRUE))
}
, args = c("EducationLevel"))
# for (qsn in c("Q124742","Q124122"))
# for (qsn in grep("Q12(.{4})(?!\\.fctr)", names(glbObsTrn), value = TRUE, perl = TRUE))
for (qsn in grep("Q", glbFeatsExclude, fixed = TRUE, value = TRUE))
glbFeatsDerive[[paste0(qsn, ".fctr")]] <- list(
mapfn = function(raw1) {
raw1[raw1 %in% ""] <- "NA"
rawVal <- unique(raw1)
if (length(setdiff(rawVal, (expVal <- c("NA", "No", "Ys")))) == 0) {
raw1 <- gsub("Yes", "Ys", raw1, fixed = TRUE)
if (length(setdiff(rawVal, expVal)) > 0)
stop(qsn, " vals: ", paste0(rawVal, collapse = "|"),
" does not match expectation: ", paste0(expVal, collapse = "|"))
} else
if (length(setdiff(rawVal, (expVal <- c("NA", "Me", "Circumstances")))) == 0) {
raw1 <- gsub("Circumstances", "Cs", raw1, fixed = TRUE)
if (length(setdiff(rawVal, expVal)) > 0)
stop(qsn, " vals: ", paste0(rawVal, collapse = "|"),
" does not match expectation: ", paste0(expVal, collapse = "|"))
} else
if (length(setdiff(rawVal, (expVal <- c("NA", "Grrr people", "Yay people!")))) == 0) {
raw1 <- gsub("Grrr people", "Gr", raw1, fixed = TRUE)
raw1 <- gsub("Yay people!", "Yy", raw1, fixed = TRUE)
if (length(setdiff(rawVal, expVal)) > 0)
stop(qsn, " vals: ", paste0(rawVal, collapse = "|"),
" does not match expectation: ", paste0(expVal, collapse = "|"))
} else
if (length(setdiff(rawVal, (expVal <- c("NA", "Idealist", "Pragmatist")))) == 0) {
raw1 <- gsub("Idealist" , "Id", raw1, fixed = TRUE)
raw1 <- gsub("Pragmatist", "Pr", raw1, fixed = TRUE)
if (length(setdiff(rawVal, expVal)) > 0)
stop(qsn, " vals: ", paste0(rawVal, collapse = "|"),
" does not match expectation: ", paste0(expVal, collapse = "|"))
} else
if (length(setdiff(rawVal, (expVal <- c("NA", "Private", "Public")))) == 0) {
raw1 <- gsub("Private", "Pt", raw1, fixed = TRUE)
raw1 <- gsub("Public" , "Pc", raw1, fixed = TRUE)
if (length(setdiff(rawVal, expVal)) > 0)
stop(qsn, " vals: ", paste0(rawVal, collapse = "|"),
" does not match expectation: ", paste0(expVal, collapse = "|"))
}
return(relevel(as.factor(raw1), ref = "NA"))
}
, args = c(qsn))
# If imputation of missing data is not working ...
# glbFeatsDerive[["FertilityRate.nonNA"]] <- list(
# mapfn = function(FertilityRate, Region) {
# RegionMdn <- tapply(FertilityRate, Region, FUN = median, na.rm = TRUE)
#
# retVal <- FertilityRate
# retVal[is.na(FertilityRate)] <- RegionMdn[Region[is.na(FertilityRate)]]
# return(retVal)
# }
# , args = c("FertilityRate", "Region"))
# mapfn = function(HOSPI.COST) { return(cut(HOSPI.COST, 5, breaks = c(0, 100000, 200000, 300000, 900000), labels = NULL)) }
# mapfn = function(Rasmussen) { return(ifelse(sign(Rasmussen) >= 0, 1, 0)) }
# mapfn = function(startprice) { return(startprice ^ (1/2)) }
# mapfn = function(startprice) { return(log(startprice)) }
# mapfn = function(startprice) { return(exp(-startprice / 20)) }
# mapfn = function(startprice) { return(scale(log(startprice))) }
# mapfn = function(startprice) { return(sign(sprice.predict.diff) * (abs(sprice.predict.diff) ^ (1/10))) }
# factor
# mapfn = function(PropR) { return(as.factor(ifelse(PropR >= 0.5, "Y", "N"))) }
# mapfn = function(productline, description) { as.factor(gsub(" ", "", productline)) }
# mapfn = function(purpose) { return(relevel(as.factor(purpose), ref="all_other")) }
# mapfn = function(raw) { tfr_raw <- as.character(cut(raw, 5));
# tfr_raw[is.na(tfr_raw)] <- "NA.my";
# return(as.factor(tfr_raw)) }
# mapfn = function(startprice.log10) { return(cut(startprice.log10, 3)) }
# mapfn = function(startprice.log10) { return(cut(sprice.predict.diff, c(-1000, -100, -10, -1, 0, 1, 10, 100, 1000))) }
# , args = c("<arg1>"))
# multiple args
# mapfn = function(id, date) { return(paste(as.character(id), as.character(date), sep = "#")) }
# mapfn = function(PTS, oppPTS) { return(PTS - oppPTS) }
# mapfn = function(startprice.log10.predict, startprice) {
# return(spdiff <- (10 ^ startprice.log10.predict) - startprice) }
# mapfn = function(productline, description) { as.factor(
# paste(gsub(" ", "", productline), as.numeric(nchar(description) > 0), sep = "*")) }
# mapfn = function(.src, .pos) {
# return(paste(.src, sprintf("%04d",
# ifelse(.src == "Train", .pos, .pos - 7049)
# ), sep = "#")) }
# # If glbObsAll is not sorted in the desired manner
# mapfn=function(Week) { return(coredata(lag(zoo(orderBy(~Week, glbObsAll)$ILI), -2, na.pad=TRUE))) }
# mapfn=function(ILI) { return(coredata(lag(zoo(ILI), -2, na.pad=TRUE))) }
# mapfn=function(ILI.2.lag) { return(log(ILI.2.lag)) }
# glbFeatsDerive[["<var1>"]] <- glbFeatsDerive[["<var2>"]]
# tst <- "descr.my"; args_lst <- NULL; for (arg in glbFeatsDerive[[tst]]$args) args_lst[[arg]] <- glbObsAll[, arg]; print(head(args_lst[[arg]])); print(head(drv_vals <- do.call(glbFeatsDerive[[tst]]$mapfn, args_lst)));
# print(which_ix <- which(args_lst[[arg]] == 0.75)); print(drv_vals[which_ix]);
glbFeatsDateTime <- list()
# Use OlsonNames() to enumerate supported time zones
# glbFeatsDateTime[["<DateTimeFeat>"]] <-
# c(format = "%Y-%m-%d %H:%M:%S" or "%m/%e/%y", timezone = "US/Eastern", impute.na = TRUE,
# last.ctg = FALSE, poly.ctg = FALSE)
glbFeatsPrice <- NULL # or c("<price_var>")
glbFeatsImage <- list() #list(<imageFeat> = list(patchSize = 10)) # if patchSize not specified, no patch computation
glbFeatsText <- list()
Sys.setlocale("LC_ALL", "C") # For english## [1] "C/C/C/C/C/en_US.UTF-8"#glbFeatsText[["<TextFeature>"]] <- list(NULL,
# ,names = myreplacePunctuation(str_to_lower(gsub(" ", "", c(NULL,
# <comma-separated-screened-names>
# ))))
# ,rareWords = myreplacePunctuation(str_to_lower(gsub(" ", "", c(NULL,
# <comma-separated-nonSCOWL-words>
# ))))
#)
# Text Processing Step: custom modifications not present in txt_munge -> use glbFeatsDerive
# Text Processing Step: universal modifications
glb_txt_munge_filenames_pfx <- "<projectId>_mytxt_"
# Text Processing Step: tolower
# Text Processing Step: myreplacePunctuation
# Text Processing Step: removeWords
glb_txt_stop_words <- list()
# Remember to use unstemmed words
if (length(glbFeatsText) > 0) {
require(tm)
require(stringr)
glb_txt_stop_words[["<txt_var>"]] <- sort(myreplacePunctuation(str_to_lower(gsub(" ", "", c(NULL
# Remove any words from stopwords
# , setdiff(myreplacePunctuation(stopwords("english")), c("<keep_wrd1>", <keep_wrd2>"))
# Remove salutations
,"mr","mrs","dr","Rev"
# Remove misc
#,"th" # Happy [[:digit::]]+th birthday
# Remove terms present in Trn only or New only; search for "Partition post-stem"
# ,<comma-separated-terms>
# cor.y.train == NA
# ,unlist(strsplit(paste(c(NULL
# ,"<comma-separated-terms>"
# ), collapse=",")
# freq == 1; keep c("<comma-separated-terms-to-keep>")
# ,<comma-separated-terms>
# chisq.pval high (e.g. == 1); keep c("<comma-separated-terms-to-keep>")
# ,<comma-separated-terms>
# nzv.freqRatio high (e.g. >= glbFeatsNzvFreqMax); keep c("<comma-separated-terms-to-keep>")
# ,<comma-separated-terms>
)))))
}
#orderBy(~term, glb_post_stem_words_terms_df_lst[[txtFeat]][grep("^man", glb_post_stem_words_terms_df_lst[[txtFeat]]$term), ])
#glbObsAll[glb_post_stem_words_terms_mtrx_lst[[txtFeat]][, 4866] > 0, c(glb_rsp_var, txtFeat)]
# To identify terms with a specific freq
#paste0(sort(subset(glb_post_stop_words_terms_df_lst[[txtFeat]], freq == 1)$term), collapse = ",")
#paste0(sort(subset(glb_post_stem_words_terms_df_lst[[txtFeat]], freq <= 2)$term), collapse = ",")
#subset(glb_post_stem_words_terms_df_lst[[txtFeat]], term %in% c("zinger"))
# To identify terms with a specific freq &
# are not stemmed together later OR is value of color.fctr (e.g. gold)
#paste0(sort(subset(glb_post_stop_words_terms_df_lst[[txtFeat]], (freq == 1) & !(term %in% c("blacked","blemish","blocked","blocks","buying","cables","careful","carefully","changed","changing","chargers","cleanly","cleared","connect","connects","connected","contains","cosmetics","default","defaulting","defective","definitely","describe","described","devices","displays","drop","drops","engravement","excellant","excellently","feels","fix","flawlessly","frame","framing","gentle","gold","guarantee","guarantees","handled","handling","having","install","iphone","iphones","keeped","keeps","known","lights","line","lining","liquid","liquidation","looking","lots","manuals","manufacture","minis","most","mostly","network","networks","noted","opening","operated","performance","performs","person","personalized","photograph","physically","placed","places","powering","pre","previously","products","protection","purchasing","returned","rotate","rotation","running","sales","second","seconds","shipped","shuts","sides","skin","skinned","sticker","storing","thats","theres","touching","unusable","update","updates","upgrade","weeks","wrapped","verified","verify") ))$term), collapse = ",")
#print(subset(glb_post_stem_words_terms_df_lst[[txtFeat]], (freq <= 2)))
#glbObsAll[which(terms_mtrx[, 229] > 0), glbFeatsText]
# To identify terms with cor.y == NA
#orderBy(~-freq+term, subset(glb_post_stop_words_terms_df_lst[[txtFeat]], is.na(cor.y)))
#paste(sort(subset(glb_post_stop_words_terms_df_lst[[txtFeat]], is.na(cor.y))[, "term"]), collapse=",")
#orderBy(~-freq+term, subset(glb_post_stem_words_terms_df_lst[[txtFeat]], is.na(cor.y)))
# To identify terms with low cor.y.abs
#head(orderBy(~cor.y.abs+freq+term, subset(glb_post_stem_words_terms_df_lst[[txtFeat]], !is.na(cor.y))), 5)
# To identify terms with high chisq.pval
#subset(glb_post_stem_words_terms_df_lst[[txtFeat]], chisq.pval > 0.99)
#paste0(sort(subset(glb_post_stem_words_terms_df_lst[[txtFeat]], (chisq.pval > 0.99) & (freq <= 10))$term), collapse=",")
#paste0(sort(subset(glb_post_stem_words_terms_df_lst[[txtFeat]], (chisq.pval > 0.9))$term), collapse=",")
#head(orderBy(~-chisq.pval+freq+term, glb_post_stem_words_terms_df_lst[[txtFeat]]), 5)
#glbObsAll[glb_post_stem_words_terms_mtrx_lst[[txtFeat]][, 68] > 0, glbFeatsText]
#orderBy(~term, glb_post_stem_words_terms_df_lst[[txtFeat]][grep("^m", glb_post_stem_words_terms_df_lst[[txtFeat]]$term), ])
# To identify terms with high nzv.freqRatio
#summary(glb_post_stem_words_terms_df_lst[[txtFeat]]$nzv.freqRatio)
#paste0(sort(setdiff(subset(glb_post_stem_words_terms_df_lst[[txtFeat]], (nzv.freqRatio >= glbFeatsNzvFreqMax) & (freq < 10) & (chisq.pval >= 0.05))$term, c( "128gb","3g","4g","gold","ipad1","ipad3","ipad4","ipadair2","ipadmini2","manufactur","spacegray","sprint","tmobil","verizon","wifion"))), collapse=",")
# To identify obs with a txt term
#tail(orderBy(~-freq+term, glb_post_stop_words_terms_df_lst[[txtFeat]]), 20)
#mydspObs(list(descr.my.contains="non"), cols=c("color", "carrier", "cellular", "storage"))
#grep("ever", dimnames(terms_stop_mtrx)$Terms)
#which(terms_stop_mtrx[, grep("ipad", dimnames(terms_stop_mtrx)$Terms)] > 0)
#glbObsAll[which(terms_stop_mtrx[, grep("16", dimnames(terms_stop_mtrx)$Terms)[1]] > 0), c(glbFeatsCategory, "storage", txtFeat)]
# Text Processing Step: screen for names # Move to glbFeatsText specs section in order of text processing steps
# glbFeatsText[["<txtFeat>"]]$names <- myreplacePunctuation(str_to_lower(gsub(" ", "", c(NULL
# # Person names for names screening
# ,<comma-separated-list>
#
# # Company names
# ,<comma-separated-list>
#
# # Product names
# ,<comma-separated-list>
# ))))
# glbFeatsText[["<txtFeat>"]]$rareWords <- myreplacePunctuation(str_to_lower(gsub(" ", "", c(NULL
# # Words not in SCOWL db
# ,<comma-separated-list>
# ))))
# To identify char vectors post glbFeatsTextMap
#grep("six(.*)hour", glb_txt_chr_lst[[txtFeat]], ignore.case = TRUE, value = TRUE)
#grep("[S|s]ix(.*)[H|h]our", glb_txt_chr_lst[[txtFeat]], value = TRUE)
# To identify whether terms shd be synonyms
#orderBy(~term, glb_post_stop_words_terms_df_lst[[txtFeat]][grep("^moder", glb_post_stop_words_terms_df_lst[[txtFeat]]$term), ])
# term_row_df <- glb_post_stop_words_terms_df_lst[[txtFeat]][grep("^came$", glb_post_stop_words_terms_df_lst[[txtFeat]]$term), ]
#
# cor(glb_post_stop_words_terms_mtrx_lst[[txtFeat]][glbObsAll$.lcn == "Fit", term_row_df$pos], glbObsTrn[, glb_rsp_var], use="pairwise.complete.obs")
# To identify which stopped words are "close" to a txt term
#sort(glbFeatsCluster)
# Text Processing Step: stemDocument
# To identify stemmed txt terms
#glb_post_stop_words_terms_df_lst[[txtFeat]][grep("^la$", glb_post_stop_words_terms_df_lst[[txtFeat]]$term), ]
#orderBy(~term, glb_post_stem_words_terms_df_lst[[txtFeat]][grep("^con", glb_post_stem_words_terms_df_lst[[txtFeat]]$term), ])
#glbObsAll[which(terms_stem_mtrx[, grep("use", dimnames(terms_stem_mtrx)$Terms)[[1]]] > 0), c(glbFeatsId, "productline", txtFeat)]
#glbObsAll[which(TfIdf_stem_mtrx[, 191] > 0), c(glbFeatsId, glbFeatsCategory, txtFeat)]
#glbObsAll[which(glb_post_stop_words_terms_mtrx_lst[[txtFeat]][, 6165] > 0), c(glbFeatsId, glbFeatsCategory, txtFeat)]
#which(glbObsAll$UniqueID %in% c(11915, 11926, 12198))
# Text Processing Step: mycombineSynonyms
# To identify which terms are associated with not -> combine "could not" & "couldn't"
#findAssocs(glb_full_DTM_lst[[txtFeat]], "not", 0.05)
# To identify which synonyms should be combined
#orderBy(~term, glb_post_stem_words_terms_df_lst[[txtFeat]][grep("^c", glb_post_stem_words_terms_df_lst[[txtFeat]]$term), ])
chk_comb_cor <- function(syn_lst) {
# cor(terms_stem_mtrx[glbObsAll$.src == "Train", grep("^(damag|dent|ding)$", dimnames(terms_stem_mtrx)[[2]])], glbObsTrn[, glb_rsp_var], use="pairwise.complete.obs")
print(subset(glb_post_stem_words_terms_df_lst[[txtFeat]], term %in% syn_lst$syns))
print(subset(get_corpus_terms(tm_map(glbFeatsTextCorpus[[txtFeat]], mycombineSynonyms, list(syn_lst), lazy=FALSE)), term == syn_lst$word))
# cor(terms_stop_mtrx[glbObsAll$.src == "Train", grep("^(damage|dent|ding)$", dimnames(terms_stop_mtrx)[[2]])], glbObsTrn[, glb_rsp_var], use="pairwise.complete.obs")
# cor(rowSums(terms_stop_mtrx[glbObsAll$.src == "Train", grep("^(damage|dent|ding)$", dimnames(terms_stop_mtrx)[[2]])]), glbObsTrn[, glb_rsp_var], use="pairwise.complete.obs")
}
#chk_comb_cor(syn_lst=list(word="cabl", syns=c("cabl", "cord")))
#chk_comb_cor(syn_lst=list(word="damag", syns=c("damag", "dent", "ding")))
#chk_comb_cor(syn_lst=list(word="dent", syns=c("dent", "ding")))
#chk_comb_cor(syn_lst=list(word="use", syns=c("use", "usag")))
glbFeatsTextSynonyms <- list()
# list parsed to collect glbFeatsText[[<txtFeat>]]$vldTerms
# glbFeatsTextSynonyms[["Hdln.my"]] <- list(NULL
# # people in places
# , list(word = "australia", syns = c("australia", "australian"))
# , list(word = "italy", syns = c("italy", "Italian"))
# , list(word = "newyork", syns = c("newyork", "newyorker"))
# , list(word = "Pakistan", syns = c("Pakistan", "Pakistani"))
# , list(word = "peru", syns = c("peru", "peruvian"))
# , list(word = "qatar", syns = c("qatar", "qatari"))
# , list(word = "scotland", syns = c("scotland", "scotish"))
# , list(word = "Shanghai", syns = c("Shanghai", "Shanzhai"))
# , list(word = "venezuela", syns = c("venezuela", "venezuelan"))
#
# # companies - needs to be data dependent
# # - e.g. ensure BNP in this experiment/feat always refers to BNPParibas
#
# # general synonyms
# , list(word = "Create", syns = c("Create","Creator"))
# , list(word = "cute", syns = c("cute","cutest"))
# , list(word = "Disappear", syns = c("Disappear","Fadeout"))
# , list(word = "teach", syns = c("teach", "taught"))
# , list(word = "theater", syns = c("theater", "theatre", "theatres"))
# , list(word = "understand", syns = c("understand", "understood"))
# , list(word = "weak", syns = c("weak", "weaken", "weaker", "weakest"))
# , list(word = "wealth", syns = c("wealth", "wealthi"))
#
# # custom synonyms (phrases)
#
# # custom synonyms (names)
# )
#glbFeatsTextSynonyms[["<txtFeat>"]] <- list(NULL
# , list(word="<stem1>", syns=c("<stem1>", "<stem1_2>"))
# )
for (txtFeat in names(glbFeatsTextSynonyms))
for (entryIx in 1:length(glbFeatsTextSynonyms[[txtFeat]])) {
glbFeatsTextSynonyms[[txtFeat]][[entryIx]]$word <-
str_to_lower(glbFeatsTextSynonyms[[txtFeat]][[entryIx]]$word)
glbFeatsTextSynonyms[[txtFeat]][[entryIx]]$syns <-
str_to_lower(glbFeatsTextSynonyms[[txtFeat]][[entryIx]]$syns)
}
glbFeatsTextSeed <- 181
# tm options include: check tm::weightSMART
glb_txt_terms_control <- list( # Gather model performance & run-time stats
# weighting = function(x) weightSMART(x, spec = "nnn")
# weighting = function(x) weightSMART(x, spec = "lnn")
# weighting = function(x) weightSMART(x, spec = "ann")
# weighting = function(x) weightSMART(x, spec = "bnn")
# weighting = function(x) weightSMART(x, spec = "Lnn")
#
weighting = function(x) weightSMART(x, spec = "ltn") # default
# weighting = function(x) weightSMART(x, spec = "lpn")
#
# weighting = function(x) weightSMART(x, spec = "ltc")
#
# weighting = weightBin
# weighting = weightTf
# weighting = weightTfIdf # : default
# termFreq selection criteria across obs: tm default: list(global=c(1, Inf))
, bounds = list(global = c(1, Inf))
# wordLengths selection criteria: tm default: c(3, Inf)
, wordLengths = c(1, Inf)
)
glb_txt_cor_var <- glb_rsp_var # : default # or c(<feat>)
# select one from c("union.top.val.cor", "top.cor", "top.val", default: "top.chisq", "sparse")
glbFeatsTextFilter <- "top.chisq"
glbFeatsTextTermsMax <- rep(10, length(glbFeatsText)) # :default
names(glbFeatsTextTermsMax) <- names(glbFeatsText)
# Text Processing Step: extractAssoc
glbFeatsTextAssocCor <- rep(1, length(glbFeatsText)) # :default
names(glbFeatsTextAssocCor) <- names(glbFeatsText)
# Remember to use stemmed terms
glb_important_terms <- list()
# Text Processing Step: extractPatterns (ngrams)
glbFeatsTextPatterns <- list()
#glbFeatsTextPatterns[[<txtFeat>>]] <- list()
#glbFeatsTextPatterns[[<txtFeat>>]] <- c(metropolitan.diary.colon = "Metropolitan Diary:")
# Have to set it even if it is not used
# Properties:
# numrows(glb_feats_df) << numrows(glbObsFit
# Select terms that appear in at least 0.2 * O(FP/FN(glbObsOOB)) ???
# numrows(glbObsOOB) = 1.1 * numrows(glbObsNew) ???
glb_sprs_thresholds <- NULL # or c(<txtFeat1> = 0.988, <txtFeat2> = 0.970, <txtFeat3> = 0.970)
glbFctrMaxUniqVals <- 20 # default: 20
glb_impute_na_data <- FALSE # or TRUE
glb_mice_complete.seed <- 144 # or any integer
glbFeatsCluster <- paste(grep("^Q.", glbFeatsExclude, value = TRUE), "fctr", sep = ".") # NULL : glbFeatsCluster <- c("YOB.Age.fctr", "Gender.fctr", "Income.fctr",
# # "Hhold.fctr",
# "Edn.fctr",
# paste(grep("^Q.", glbFeatsExclude, value = TRUE), "fctr", sep = ".")) # NULL : default or c("<feat1>", "<feat2>")
# glbFeatsCluster <- grep(paste0("[",
# toupper(paste0(substr(glbFeatsText, 1, 1), collapse = "")),
# "]\\.[PT]\\."),
# names(glbObsAll), value = TRUE)
glb_cluster.seed <- 189 # or any integer
glbClusterEntropyVar <- NULL # c(glb_rsp_var, as.factor(cut(glb_rsp_var, 3)), default: NULL)
glbFeatsClusterVarsExclude <- FALSE # default FALSE
glb_interaction_only_feats <- NULL # : default or c(<parent_feat> = "<child_feat>")
glbFeatsNzvFreqMax <- 19 # 19 : caret default
glbFeatsNzvUniqMin <- 10 # 10 : caret default
glbRFESizes <- list()
#glbRFESizes[["mdlFamily"]] <- c(4, 8, 16, 32, 64, 67, 68, 69) # Accuracy@69/70 = 0.8258
# glbRFESizes[["RFE.X"]] <- c(96, 112, 120, 124, 128, 129, 130, 131, 132, 133, 135, 138, 142, 157, 187, 247) # accuracy(131) = 0.6285
# glbRFESizes[["Final"]] <- c(8, 16, 32, 40, 44, 46, 48, 49, 50, 51, 52, 56, 64, 96, 128, 247) # accuracy(49) = 0.6164
glbRFEResults <- NULL
glbObsFitOutliers <- list()
# If outliers.n >= 10; consider concatenation of interaction vars
# glbObsFitOutliers[["<mdlFamily>"]] <- c(NULL
# is.na(.rstudent)
# max(.rstudent)
# is.na(.dffits)
# .hatvalues >= 0.99
# -38,167,642 < minmax(.rstudent) < 49,649,823
# , <comma-separated-<glbFeatsId>>
# )
glbObsTrnOutliers <- list()
glbObsTrnOutliers[["Final"]] <- union(glbObsFitOutliers[["All.X"]],
c(NULL
))
# Modify mdlId to (build & extract) "<FamilyId>#<Fit|Trn>#<caretMethod>#<preProc1.preProc2>#<samplingMethod>"
glb_models_lst <- list(); glb_models_df <- data.frame()
# Add xgboost algorithm
# Regression
if (glb_is_regression) {
glbMdlMethods <- c(NULL
# deterministic
#, "lm", # same as glm
, "glm", "bayesglm", "glmnet"
, "rpart"
# non-deterministic
, "gbm", "rf"
# Unknown
, "nnet" , "avNNet" # runs 25 models per cv sample for tunelength=5
, "svmLinear", "svmLinear2"
, "svmPoly" # runs 75 models per cv sample for tunelength=5
, "svmRadial"
, "earth"
, "bagEarth" # Takes a long time
,"xgbLinear","xgbTree"
)
} else
# Classification - Add ada (auto feature selection)
if (glb_is_binomial)
glbMdlMethods <- c(NULL
# deterministic
, "bagEarth" # Takes a long time
, "glm", "bayesglm", "glmnet"
, "nnet"
, "rpart"
# non-deterministic
, "gbm"
, "avNNet" # runs 25 models per cv sample for tunelength=5
, "rf"
# Unknown
, "lda", "lda2"
# svm models crash when predict is called -> internal to kernlab it should call predict without .outcome
, "svmLinear", "svmLinear2"
, "svmPoly" # runs 75 models per cv sample for tunelength=5
, "svmRadial"
, "earth"
,"xgbLinear","xgbTree"
) else
glbMdlMethods <- c(NULL
# deterministic
,"glmnet"
# non-deterministic
,"rf"
# Unknown
,"gbm","rpart","xgbLinear","xgbTree"
)
glbMdlFamilies <- list(); glb_mdl_feats_lst <- list()
# family: Choose from c("RFE.X", "Csm.X", "All.X", "Best.Interact") %*% c(NUll, ".NOr", ".Inc")
# RFE = "Recursive Feature Elimination"
# Csm = CuStoM
# NOr = No OutlieRs
# Inc = INteraCt
# methods: Choose from c(NULL, <method>, glbMdlMethods)
#glbMdlFamilies[["RFE.X"]] <- c("glmnet", "glm") # non-NULL vector is mandatory
if (glb_is_classification && !glb_is_binomial) {
# glm does not work for multinomial
glbMdlFamilies[["All.X"]] <- c("glmnet")
} else {
# glbMdlFamilies[["All.X"]] <- c("glmnet", "glm")
glbMdlFamilies[["All.X"]] <- c("glmnet")
# glbMdlFamilies[["RFE.X"]] <- c("glmnet", "glm")
# glbMdlFamilies[["RFE.X"]] <- setdiff(glbMdlMethods, c(NULL
# , "bayesglm" # error: Error in trControl$classProbs && any(classLevels != make.names(classLevels)) : invalid 'x' type in 'x && y'
# , "lda","lda2" # error: Error in lda.default(x, grouping, ...) : variable 236 appears to be constant within groups
# , "svmLinear" # Error in .local(object, ...) : test vector does not match model ! In addition: Warning messages:
# , "svmLinear2" # SVM has not been trained using `probability = TRUE`, probabilities not available for predictions
# , "svmPoly" # runs 75 models per cv sample for tunelength=5 # took > 2 hrs # Error in .local(object, ...) : test vector does not match model !
# , "svmRadial" # didn't bother
# ,"xgbLinear","xgbTree" # Need clang-omp compiler; Upgrade to Revolution R 3.2.3 (3.2.2 current); https://github.com/dmlc/xgboost/issues/276 thread
# ))
}
# glbMdlFamilies[["All.X.Inc"]] <- glbMdlFamilies[["All.X"]] # value not used
# glbMdlFamilies[["RFE.X.Inc"]] <- glbMdlFamilies[["RFE.X"]] # value not used
# Check if interaction features make RFE better
# glbMdlFamilies[["CSM.X"]] <- setdiff(glbMdlMethods, c("lda", "lda2")) # crashing due to category:.clusterid ??? #c("glmnet", "glm") # non-NULL list is mandatory
# glb_mdl_feats_lst[["CSM.X"]] <- c(NULL
# , <comma-separated-features-vector>
# )
# dAFeats.CSM.X %<d-% c(NULL
# # Interaction feats up to varImp(RFE.X.glmnet) >= 50
# , <comma-separated-features-vector>
# , setdiff(myextract_actual_feats(predictors(glbRFEResults)), c(NULL
# , <comma-separated-features-vector>
# ))
# )
# glb_mdl_feats_lst[["CSM.X"]] <- "%<d-% dAFeats.CSM.X"
# glbMdlFamilies[["Final"]] <- c(NULL) # NULL vector acceptable # c("glmnet", "glm")
glbMdlAllowParallel <- list()
#glbMdlAllowParallel[["Final##rcv#glmnet"]] <- FALSE
glbMdlAllowParallel[["All.X##rcv#glm"]] <- FALSE
# Check if tuning parameters make fit better; make it mdlFamily customizable ?
glbMdlTuneParams <- data.frame()
# When glmnet crashes at model$grid with error: ???
AllX__rcv_glmnetTuneParams <- rbind(data.frame()
,data.frame(parameter = "alpha", vals = "0.100 0.325 0.550 0.775 1.000")
,data.frame(parameter = "lambda", vals = "0.0356818417 0.05 0.06367626 0.07 0.09167068")
)
FinalAllX__rcv_glmnetTuneParams <- rbind(data.frame()
,data.frame(parameter = "alpha", vals = "0.100 0.325 0.550 0.775 1.000")
,data.frame(parameter = "lambda", vals = "6.451187e-03 0.02 2.994376e-02 0.04 0.05343633")
)
glbMdlTuneParams <- rbind(glbMdlTuneParams,
cbind(data.frame(mdlId = "All.X##rcv#glmnet"), AllX__rcv_glmnetTuneParams),
cbind(data.frame(mdlId = "Final.All.X##rcv#glmnet"), FinalAllX__rcv_glmnetTuneParams))
#avNNet
# size=[1] 3 5 7 9; decay=[0] 1e-04 0.001 0.01 0.1; bag=[FALSE]; RMSE=1.3300906
#bagEarth
# degree=1 [2] 3; nprune=64 128 256 512 [1024]; RMSE=0.6486663 (up)
bagEarthTuneParams <- rbind(data.frame()
,data.frame(parameter = "degree", vals = "1")
,data.frame(parameter = "nprune", vals = "256")
)
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams,
# cbind(data.frame(mdlId = "Final.RFE.X.Inc##rcv#bagEarth"),
# bagEarthTuneParams))
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "bagEarth", parameter = "nprune", vals = "256")
# ,data.frame(method = "bagEarth", parameter = "degree", vals = "2")
# ))
#earth
# degree=[1]; nprune=2 [9] 17 25 33; RMSE=0.1334478
#gbm
# shrinkage=0.05 [0.10] 0.15 0.20 0.25; n.trees=100 150 200 [250] 300; interaction.depth=[1] 2 3 4 5; n.minobsinnode=[10]; RMSE=0.2008313
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "gbm", parameter = "shrinkage", min = 0.05, max = 0.25, by = 0.05)
# ,data.frame(method = "gbm", parameter = "n.trees", min = 100, max = 300, by = 50)
# ,data.frame(method = "gbm", parameter = "interaction.depth", min = 1, max = 5, by = 1)
# ,data.frame(method = "gbm", parameter = "n.minobsinnode", min = 10, max = 10, by = 10)
# #seq(from=0.05, to=0.25, by=0.05)
# ))
#glmnet
# alpha=0.100 [0.325] 0.550 0.775 1.000; lambda=0.0005232693 0.0024288010 0.0112734954 [0.0523269304] 0.2428800957; RMSE=0.6164891
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "glmnet", parameter = "alpha", vals = "0.550 0.775 0.8875 0.94375 1.000")
# ,data.frame(method = "glmnet", parameter = "lambda", vals = "9.858855e-05 0.0001971771 0.0009152152 0.0042480525 0.0197177130")
# ))
#nnet
# size=3 5 [7] 9 11; decay=0.0001 0.001 0.01 [0.1] 0.2; RMSE=0.9287422
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "nnet", parameter = "size", vals = "3 5 7 9 11")
# ,data.frame(method = "nnet", parameter = "decay", vals = "0.0001 0.0010 0.0100 0.1000 0.2000")
# ))
#rf # Don't bother; results are not deterministic
# mtry=2 35 68 [101] 134; RMSE=0.1339974
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "rf", parameter = "mtry", vals = "2 5 9 13 17")
# ))
#rpart
# cp=0.020 [0.025] 0.030 0.035 0.040; RMSE=0.1770237
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "rpart", parameter = "cp", vals = "0.004347826 0.008695652 0.017391304 0.021739130 0.034782609")
# ))
#svmLinear
# C=0.01 0.05 [0.10] 0.50 1.00 2.00 3.00 4.00; RMSE=0.1271318; 0.1296718
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "svmLinear", parameter = "C", vals = "0.01 0.05 0.1 0.5 1")
# ))
#svmLinear2
# cost=0.0625 0.1250 [0.25] 0.50 1.00; RMSE=0.1276354
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "svmLinear2", parameter = "cost", vals = "0.0625 0.125 0.25 0.5 1")
# ))
#svmPoly
# degree=[1] 2 3 4 5; scale=0.01 0.05 [0.1] 0.5 1; C=0.50 1.00 [2.00] 3.00 4.00; RMSE=0.1276130
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method="svmPoly", parameter="degree", min=1, max=5, by=1) #seq(1, 5, 1)
# ,data.frame(method="svmPoly", parameter="scale", vals="0.01, 0.05, 0.1, 0.5, 1")
# ,data.frame(method="svmPoly", parameter="C", vals="0.50, 1.00, 2.00, 3.00, 4.00")
# ))
#svmRadial
# sigma=[0.08674323]; C=0.25 0.50 1.00 [2.00] 4.00; RMSE=0.1614957
#glb2Sav(); all.equal(sav_models_df, glb_models_df)
pkgPreprocMethods <-
# caret version: 6.0.068 # packageVersion("caret")
# operations are applied in this order: zero-variance filter, near-zero variance filter, Box-Cox/Yeo-Johnson/exponential transformation, centering, scaling, range, imputation, PCA, ICA then spatial sign
# *Impute methods needed only if NAs are fed to myfit_mdl
# Also, ordered.factor in caret creates features as Edn.fctr^4 which is treated as an exponent by bagImpute
c(NULL
,"zv", "nzv"
,"BoxCox", "YeoJohnson", "expoTrans"
,"center", "scale", "center.scale", "range"
,"knnImpute", "bagImpute", "medianImpute"
,"zv.pca", "ica", "spatialSign"
,"conditionalX")
glbMdlPreprocMethods <- list(NULL # : default
# "All.X" = list("glmnet" = union(setdiff(pkgPreprocMethods,
# c("knnImpute", "bagImpute", "medianImpute")),
# # NULL))
# c("nzv.spatialSign")))
)
# glbMdlPreprocMethods[["RFE.X"]] <- list("glmnet" = union(unlist(glbMdlPreprocMethods[["All.X"]]),
# "nzv.pca.spatialSign"))
# Baseline prediction model feature(s)
glb_Baseline_mdl_var <- NULL # or c("<feat>")
glbMdlMetric_terms <- NULL # or matrix(c(
# 0,1,2,3,4,
# 2,0,1,2,3,
# 4,2,0,1,2,
# 6,4,2,0,1,
# 8,6,4,2,0
# ), byrow=TRUE, nrow=5)
glbMdlMetricSummary <- NULL # or "<metric_name>"
glbMdlMetricMaximize <- NULL # or FALSE (TRUE is not the default for both classification & regression)
glbMdlMetricSummaryFn <- NULL # or function(data, lev=NULL, model=NULL) {
# confusion_mtrx <- t(as.matrix(confusionMatrix(data$pred, data$obs)))
# #print(confusion_mtrx)
# #print(confusion_mtrx * glbMdlMetric_terms)
# metric <- sum(confusion_mtrx * glbMdlMetric_terms) / nrow(data)
# names(metric) <- glbMdlMetricSummary
# return(metric)
# }
glbMdlCheckRcv <- FALSE # Turn it on when needed; otherwise takes long time
glb_rcv_n_folds <- 3 # or NULL
glb_rcv_n_repeats <- 3 # or NULL
glb_clf_proba_threshold <- NULL # 0.5
# Model selection criteria
if (glb_is_regression)
glbMdlMetricsEval <- c("min.RMSE.OOB", "max.R.sq.OOB", "min.elapsedtime.everything",
"max.Adj.R.sq.fit", "min.RMSE.fit")
#glbMdlMetricsEval <- c("min.RMSE.fit", "max.R.sq.fit", "max.Adj.R.sq.fit")
if (glb_is_classification) {
if (glb_is_binomial)
glbMdlMetricsEval <-
c("max.Accuracy.OOB", "max.AUCROCR.OOB", "max.AUCpROC.OOB",
"min.elapsedtime.everything",
# "min.aic.fit",
"max.Accuracy.fit") else
glbMdlMetricsEval <- c("max.Accuracy.OOB", "max.Kappa.OOB", "min.elapsedtime.everything")
}
# select from NULL [no ensemble models], "auto" [all models better than MFO or Baseline], c(mdl_ids in glb_models_lst) [Typically top-rated models in auto]
glbMdlEnsemble <- NULL #"auto"
# "%<d-% setdiff(mygetEnsembleAutoMdlIds(), 'CSM.X.rf')"
# c(<comma-separated-mdlIds>
# )
# Only for classifications; for regressions remove "(.*)\\.prob" form the regex
# tmp_fitobs_df <- glbObsFit[, grep(paste0("^", gsub(".", "\\.", mygetPredictIds$value, fixed = TRUE), "CSM\\.X\\.(.*)\\.prob"), names(glbObsFit), value = TRUE)]; cor_mtrx <- cor(tmp_fitobs_df); cor_vctr <- sort(cor_mtrx[row.names(orderBy(~-Overall, varImp(glb_models_lst[["Ensemble.repeatedcv.glmnet"]])$imp))[1], ]); summary(cor_vctr); cor_vctr
#ntv.glm <- glm(reformulate(indepVar, glb_rsp_var), family = "binomial", data = glbObsFit)
#step.glm <- step(ntv.glm)
glbMdlSelId <- "All.X##rcv#glmnet" #select from c(NULL, "All.X##rcv#glmnet", "RFE.X##rcv#glmnet", <mdlId>)
glbMdlFinId <- NULL #select from c(NULL, glbMdlSelId)
glb_dsp_cols <- c(".pos", glbFeatsId, glbFeatsCategory, glb_rsp_var
# List critical cols excl. above
)
# Output specs
# lclgetfltout_df <- function(obsOutFinDf) {
# require(tidyr)
# obsOutFinDf <- obsOutFinDf %>%
# tidyr::separate("ImageId.x.y", c(".src", ".pos", "x", "y"),
# sep = "#", remove = TRUE, extra = "merge")
# # mnm prefix stands for max_n_mean
# mnmout_df <- obsOutFinDf %>%
# dplyr::group_by(.pos) %>%
# #dplyr::top_n(1, Probability1) %>% # Score = 3.9426
# #dplyr::top_n(2, Probability1) %>% # Score = ???; weighted = 3.94254;
# #dplyr::top_n(3, Probability1) %>% # Score = 3.9418; weighted = 3.94169;
# dplyr::top_n(4, Probability1) %>% # Score = ???; weighted = 3.94149;
# #dplyr::top_n(5, Probability1) %>% # Score = 3.9421; weighted = 3.94178
#
# # dplyr::summarize(xMeanN = mean(as.numeric(x)), yMeanN = mean(as.numeric(y)))
# # dplyr::summarize(xMeanN = weighted.mean(as.numeric(x), Probability1), yMeanN = mean(as.numeric(y)))
# # dplyr::summarize(xMeanN = weighted.mean(as.numeric(x), c(Probability1, 0.2357323, 0.2336925)), yMeanN = mean(as.numeric(y)))
# # dplyr::summarize(xMeanN = weighted.mean(as.numeric(x), c(Probability1)), yMeanN = mean(as.numeric(y)))
# dplyr::summarize(xMeanN = weighted.mean(as.numeric(x), c(Probability1)),
# yMeanN = weighted.mean(as.numeric(y), c(Probability1)))
#
# maxout_df <- obsOutFinDf %>%
# dplyr::group_by(.pos) %>%
# dplyr::summarize(maxProb1 = max(Probability1))
# fltout_df <- merge(maxout_df, obsOutFinDf,
# by.x = c(".pos", "maxProb1"), by.y = c(".pos", "Probability1"),
# all.x = TRUE)
# fmnout_df <- merge(fltout_df, mnmout_df,
# by.x = c(".pos"), by.y = c(".pos"),
# all.x = TRUE)
# return(fmnout_df)
# }
glbObsOut <- list(NULL
# glbFeatsId will be the first output column, by default
,vars = list()
# ,mapFn = function(obsOutFinDf) {
# }
)
#obsOutFinDf <- savobsOutFinDf
# glbObsOut$mapFn <- function(obsOutFinDf) {
# txfout_df <- dplyr::select(obsOutFinDf, -.pos.y) %>%
# dplyr::mutate(
# lunch = levels(glbObsTrn[, "lunch" ])[
# round(mean(as.numeric(glbObsTrn[, "lunch" ])), 0)],
# dinner = levels(glbObsTrn[, "dinner" ])[
# round(mean(as.numeric(glbObsTrn[, "dinner" ])), 0)],
# reserve = levels(glbObsTrn[, "reserve" ])[
# round(mean(as.numeric(glbObsTrn[, "reserve" ])), 0)],
# outdoor = levels(glbObsTrn[, "outdoor" ])[
# round(mean(as.numeric(glbObsTrn[, "outdoor" ])), 0)],
# expensive = levels(glbObsTrn[, "expensive"])[
# round(mean(as.numeric(glbObsTrn[, "expensive"])), 0)],
# liquor = levels(glbObsTrn[, "liquor" ])[
# round(mean(as.numeric(glbObsTrn[, "liquor" ])), 0)],
# table = levels(glbObsTrn[, "table" ])[
# round(mean(as.numeric(glbObsTrn[, "table" ])), 0)],
# classy = levels(glbObsTrn[, "classy" ])[
# round(mean(as.numeric(glbObsTrn[, "classy" ])), 0)],
# kids = levels(glbObsTrn[, "kids" ])[
# round(mean(as.numeric(glbObsTrn[, "kids" ])), 0)]
# )
#
# print("ObsNew output class tables:")
# print(sapply(c("lunch","dinner","reserve","outdoor",
# "expensive","liquor","table",
# "classy","kids"),
# function(feat) table(txfout_df[, feat], useNA = "ifany")))
#
# txfout_df <- txfout_df %>%
# dplyr::mutate(labels = "") %>%
# dplyr::mutate(labels =
# ifelse(lunch != "-1", paste(labels, lunch ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(dinner != "-1", paste(labels, dinner ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(reserve != "-1", paste(labels, reserve ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(outdoor != "-1", paste(labels, outdoor ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(expensive != "-1", paste(labels, expensive), labels)) %>%
# dplyr::mutate(labels =
# ifelse(liquor != "-1", paste(labels, liquor ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(table != "-1", paste(labels, table ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(classy != "-1", paste(labels, classy ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(kids != "-1", paste(labels, kids ), labels)) %>%
# dplyr::select(business_id, labels)
# return(txfout_df)
# }
#if (!is.null(glbObsOut$mapFn)) obsOutFinDf <- glbObsOut$mapFn(obsOutFinDf); print(head(obsOutFinDf))
glb_out_obs <- NULL # select from c(NULL : default to "new", "all", "new", "trn")
if (glb_is_classification && glb_is_binomial) {
# glbObsOut$vars[["Probability1"]] <-
# "%<d-% glbObsNew[, mygetPredictIds(glb_rsp_var, glbMdlFinId)$prob]"
# glbObsOut$vars[[glb_rsp_var_raw]] <-
# "%<d-% glb_map_rsp_var_to_raw(glbObsNew[,
# mygetPredictIds(glb_rsp_var, glbMdlFinId)$value])"
glbObsOut$vars[["Predictions"]] <-
"%<d-% glb_map_rsp_var_to_raw(glbObsNew[,
mygetPredictIds(glb_rsp_var, glbMdlFinId)$value])"
} else {
# glbObsOut$vars[[glbFeatsId]] <-
# "%<d-% as.integer(gsub('Test#', '', glbObsNew[, glbFeatsId]))"
glbObsOut$vars[[glb_rsp_var]] <-
"%<d-% glbObsNew[, mygetPredictIds(glb_rsp_var, glbMdlFinId)$value]"
# for (outVar in setdiff(glbFeatsExcludeLcl, glb_rsp_var_raw))
# glbObsOut$vars[[outVar]] <-
# paste0("%<d-% mean(glbObsAll[, \"", outVar, "\"], na.rm = TRUE)")
}
# glbObsOut$vars[[glb_rsp_var_raw]] <- glb_rsp_var_raw
# glbObsOut$vars[[paste0(head(unlist(strsplit(mygetPredictIds$value, "")), -1), collapse = "")]] <-
glbOutStackFnames <- # NULL #: default
c("Votes_Ensemble_cnk06_out_fin.csv") # manual stack
# c("ebayipads_finmdl_bid1_out_nnet_1.csv") # universal stack
glbOut <- list(pfx = "Q109244No_category_cnk01_rest_")
# lclImageSampleSeed <- 129
glbOutDataVizFname <- NULL # choose from c(NULL, "<projectId>_obsall.csv")
glbChunks <- list(labels = c("set_global_options_wd","set_global_options"
,"import.data","inspect.data","scrub.data","transform.data"
,"extract.features"
,"extract.features.datetime","extract.features.image","extract.features.price"
,"extract.features.text","extract.features.string"
,"extract.features.end"
,"manage.missing.data","cluster.data","partition.data.training","select.features"
,"fit.models_0","fit.models_1","fit.models_2","fit.models_3"
,"fit.data.training_0","fit.data.training_1"
,"predict.data.new"
,"display.session.info"))
# To ensure that all chunks in this script are in glbChunks
if (!is.null(chkChunksLabels <- knitr::all_labels()) && # knitr::all_labels() doesn't work in console runs
!identical(chkChunksLabels, glbChunks$labels)) {
print(sprintf("setdiff(chkChunksLabels, glbChunks$labels): %s",
setdiff(chkChunksLabels, glbChunks$labels)))
print(sprintf("setdiff(glbChunks$labels, chkChunksLabels): %s",
setdiff(glbChunks$labels, chkChunksLabels)))
}
glbChunks[["first"]] <- "scrub.data" # NULL # default: script will load envir from previous chunk
glbChunks[["last" ]] <- NULL # NULL # default: script will save envir at end of this chunk
glbChunks[["inpFilePathName"]] <- "data/Q109244No_category_cnk01_inspect.data_inspect.data.RData" # NULL: default or "data/<prvScriptName>_<lstChunkLbl>.RData"
#mysavChunk(glbOut$pfx, glbChunks[["last"]]) # called from myevlChunk
# Temporary: Delete this function (if any) from here after appropriate .RData file is saved
# Inspect max OOB FP
#chkObsOOB <- subset(glbObsOOB, !label.fctr.All.X..rcv.glmnet.is.acc)
#chkObsOOBFP <- subset(chkObsOOB, label.fctr.All.X..rcv.glmnet == "left_eye_center") %>% dplyr::mutate(Probability1 = label.fctr.All.X..rcv.glmnet.prob) %>% select(-.src, -.pos, -x, -y) %>% lclgetfltout_df() %>% mutate(obj.distance = (((as.numeric(x) - left_eye_center_x.int) ^ 2) + ((as.numeric(y) - left_eye_center_y.int) ^ 2)) ^ 0.5) %>% dplyr::top_n(5, obj.distance) %>% dplyr::top_n(5, -patch.cor)
#
#newImgObs <- glbObsNew[(glbObsNew$ImageId == "Test#0001"), ]; print(newImgObs[which.max(newImgObs$label.fctr.Final..rcv.glmnet.prob), ])
#OOBImgObs <- glbObsOOB[(glbObsOOB$ImageId == "Train#0003"), ]; print(OOBImgObs[which.max(OOBImgObs$label.fctr.All.X..rcv.glmnet.prob), ])
#mygetImage(which(glbObsAll[, glbFeatsId] == "Train#0003"), names(glbFeatsImage)[1], plot = TRUE, featHighlight = c("left_eye_center_x", "left_eye_center_y"), ovrlHighlight = c(66, 35))
# Depict process
glb_analytics_pn <- petrinet(name = "glb_analytics_pn",
trans_df = data.frame(id = 1:6,
name = c("data.training.all","data.new",
"model.selected","model.final",
"data.training.all.prediction","data.new.prediction"),
x=c( -5,-5,-15,-25,-25,-35),
y=c( -5, 5, 0, 0, -5, 5)
),
places_df=data.frame(id=1:4,
name=c("bgn","fit.data.training.all","predict.data.new","end"),
x=c( -0, -20, -30, -40),
y=c( 0, 0, 0, 0),
M0=c( 3, 0, 0, 0)
),
arcs_df = data.frame(
begin = c("bgn","bgn","bgn",
"data.training.all","model.selected","fit.data.training.all",
"fit.data.training.all","model.final",
"data.new","predict.data.new",
"data.training.all.prediction","data.new.prediction"),
end = c("data.training.all","data.new","model.selected",
"fit.data.training.all","fit.data.training.all","model.final",
"data.training.all.prediction","predict.data.new",
"predict.data.new","data.new.prediction",
"end","end")
))
#print(ggplot.petrinet(glb_analytics_pn))
print(ggplot.petrinet(glb_analytics_pn) + coord_flip())## Loading required package: grid
glb_analytics_avl_objs <- NULL
glb_chunks_df <- myadd_chunk(NULL,
ifelse(is.null(glbChunks$first), "import.data", glbChunks$first))## label step_major step_minor label_minor bgn end elapsed
## 1 scrub.data 1 0 0 10.382 NA NAStep 1.0: scrub data
chunk option: eval=
Step 1.0: scrub data
Step 1.0: scrub data
```{r scrub.data, cache=FALSE, echo=FALSE, eval=myevlChunk(glbChunks, glbOut$pfx)}
## [1] "numeric data missing in : "
## YOB Party.fctr
## 128 622
## [1] "numeric data w/ 0s in : "
## YOB.Age.dff
## 136
## [1] "numeric data w/ Infs in : "
## named integer(0)
## [1] "numeric data w/ NaNs in : "
## named integer(0)
## [1] "string data missing in : "
## Gender Income HouseholdStatus EducationLevel
## 46 445 177 410
## Party Q124742 Q124122 Q123464
## NA 1438 823 708
## Q123621 Q122769 Q122770 Q122771
## 778 644 594 587
## Q122120 Q121699 Q121700 Q120978
## 585 547 563 599
## Q121011 Q120379 Q120650 Q120472
## 571 607 655 649
## Q120194 Q120012 Q120014 Q119334
## 654 591 641 568
## Q119851 Q119650 Q118892 Q118117
## 540 578 486 479
## Q118232 Q118233 Q118237 Q117186
## 701 554 539 648
## Q117193 Q116797 Q116881 Q116953
## 655 590 635 616
## Q116601 Q116441 Q116448 Q116197
## 534 541 560 551
## Q115602 Q115777 Q115610 Q115611
## 539 578 537 487
## Q115899 Q115390 Q114961 Q114748
## 573 619 538 447
## Q115195 Q114517 Q114386 Q113992
## 525 481 521 447
## Q114152 Q113583 Q113584 Q113181
## 537 514 512 453
## Q112478 Q112512 Q112270 Q111848
## 494 460 521 398
## Q111580 Q111220 Q110740 Q109367
## 474 379 357 168
## Q108950 Q109244 Q108855 Q108617
## 204 0 438 288
## Q108856 Q108754 Q108342 Q108343
## 436 338 341 333
## Q107869 Q107491 Q106993 Q106997
## 389 366 389 396
## Q106272 Q106388 Q106389 Q106042
## 426 476 495 451
## Q105840 Q105655 Q104996 Q103293
## 487 393 400 431
## Q102906 Q102674 Q102687 Q102289
## 493 511 475 484
## Q102089 Q101162 Q101163 Q101596
## 462 498 572 477
## Q100689 Q100680 Q100562 Q99982
## 414 497 487 514
## Q100010 Q99716 Q99581 Q99480
## 445 500 466 478
## Q98869 Q98578 Q98059 Q98078
## 564 542 450 569
## Q98197 Q96024
## 528 550## Warning in rm(pltObsSmp): object 'pltObsSmp' not found## label step_major step_minor label_minor bgn end elapsed
## 1 scrub.data 1 0 0 10.382 11.298 0.916
## 2 transform.data 1 1 1 11.299 NA NAStep 1.1: transform data
## label step_major step_minor label_minor bgn end elapsed
## 2 transform.data 1 1 1 11.299 11.352 0.053
## 3 extract.features 2 0 0 11.352 NA NAStep 2.0: extract features
## label step_major step_minor label_minor bgn
## 3 extract.features 2 0 0 11.352
## 4 extract.features.datetime 2 1 1 11.368
## end elapsed
## 3 11.368 0.016
## 4 NA NAStep 2.1: extract features datetime
## label step_major step_minor label_minor bgn
## 1 extract.features.datetime.bgn 1 0 0 11.389
## end elapsed
## 1 NA NA## Warning in rm(pltObsAll): object 'pltObsAll' not found## label step_major step_minor label_minor bgn
## 4 extract.features.datetime 2 1 1 11.368
## 5 extract.features.image 2 2 2 11.399
## end elapsed
## 4 11.398 0.03
## 5 NA NAStep 2.2: extract features image
```{r extract.features.image, cache=FALSE, echo=FALSE, fig.height=5, fig.width=5, eval=myevlChunk(glbChunks, glbOut$pfx)}
## label step_major step_minor label_minor bgn end
## 1 extract.features.image.bgn 1 0 0 11.426 NA
## elapsed
## 1 NA## label step_major step_minor label_minor bgn
## 1 extract.features.image.bgn 1 0 0 11.426
## 2 extract.features.image.end 2 0 0 11.432
## end elapsed
## 1 11.432 0.006
## 2 NA NA## label step_major step_minor label_minor bgn
## 1 extract.features.image.bgn 1 0 0 11.426
## 2 extract.features.image.end 2 0 0 11.432
## end elapsed
## 1 11.432 0.006
## 2 NA NA## label step_major step_minor label_minor bgn end
## 5 extract.features.image 2 2 2 11.399 11.44
## 6 extract.features.price 2 3 3 11.440 NA
## elapsed
## 5 0.041
## 6 NAStep 2.3: extract features price
## label step_major step_minor label_minor bgn end
## 1 extract.features.price.bgn 1 0 0 11.46 NA
## elapsed
## 1 NA## label step_major step_minor label_minor bgn end
## 6 extract.features.price 2 3 3 11.440 11.466
## 7 extract.features.text 2 4 4 11.467 NA
## elapsed
## 6 0.026
## 7 NAStep 2.4: extract features text
## label step_major step_minor label_minor bgn end
## 1 extract.features.text.bgn 1 0 0 11.501 NA
## elapsed
## 1 NA## Warning in rm(tmp_allobs_df): object 'tmp_allobs_df' not found## Warning in rm(tmp_trnobs_df): object 'tmp_trnobs_df' not found## label step_major step_minor label_minor bgn end
## 7 extract.features.text 2 4 4 11.467 11.511
## 8 extract.features.string 2 5 5 11.512 NA
## elapsed
## 7 0.045
## 8 NAStep 2.5: extract features string
## label step_major step_minor label_minor bgn end
## 1 extract.features.string.bgn 1 0 0 11.54 NA
## elapsed
## 1 NA## label step_major step_minor
## 1 extract.features.string.bgn 1 0
## 2 extract.features.stringfactorize.str.vars 2 0
## label_minor bgn end elapsed
## 1 0 11.540 11.548 0.008
## 2 0 11.549 NA NA## Gender Income HouseholdStatus EducationLevel
## "Gender" "Income" "HouseholdStatus" "EducationLevel"
## Party Q124742 Q124122 Q123464
## "Party" "Q124742" "Q124122" "Q123464"
## Q123621 Q122769 Q122770 Q122771
## "Q123621" "Q122769" "Q122770" "Q122771"
## Q122120 Q121699 Q121700 Q120978
## "Q122120" "Q121699" "Q121700" "Q120978"
## Q121011 Q120379 Q120650 Q120472
## "Q121011" "Q120379" "Q120650" "Q120472"
## Q120194 Q120012 Q120014 Q119334
## "Q120194" "Q120012" "Q120014" "Q119334"
## Q119851 Q119650 Q118892 Q118117
## "Q119851" "Q119650" "Q118892" "Q118117"
## Q118232 Q118233 Q118237 Q117186
## "Q118232" "Q118233" "Q118237" "Q117186"
## Q117193 Q116797 Q116881 Q116953
## "Q117193" "Q116797" "Q116881" "Q116953"
## Q116601 Q116441 Q116448 Q116197
## "Q116601" "Q116441" "Q116448" "Q116197"
## Q115602 Q115777 Q115610 Q115611
## "Q115602" "Q115777" "Q115610" "Q115611"
## Q115899 Q115390 Q114961 Q114748
## "Q115899" "Q115390" "Q114961" "Q114748"
## Q115195 Q114517 Q114386 Q113992
## "Q115195" "Q114517" "Q114386" "Q113992"
## Q114152 Q113583 Q113584 Q113181
## "Q114152" "Q113583" "Q113584" "Q113181"
## Q112478 Q112512 Q112270 Q111848
## "Q112478" "Q112512" "Q112270" "Q111848"
## Q111580 Q111220 Q110740 Q109367
## "Q111580" "Q111220" "Q110740" "Q109367"
## Q108950 Q109244 Q108855 Q108617
## "Q108950" "Q109244" "Q108855" "Q108617"
## Q108856 Q108754 Q108342 Q108343
## "Q108856" "Q108754" "Q108342" "Q108343"
## Q107869 Q107491 Q106993 Q106997
## "Q107869" "Q107491" "Q106993" "Q106997"
## Q106272 Q106388 Q106389 Q106042
## "Q106272" "Q106388" "Q106389" "Q106042"
## Q105840 Q105655 Q104996 Q103293
## "Q105840" "Q105655" "Q104996" "Q103293"
## Q102906 Q102674 Q102687 Q102289
## "Q102906" "Q102674" "Q102687" "Q102289"
## Q102089 Q101162 Q101163 Q101596
## "Q102089" "Q101162" "Q101163" "Q101596"
## Q100689 Q100680 Q100562 Q99982
## "Q100689" "Q100680" "Q100562" "Q99982"
## Q100010 Q99716 Q99581 Q99480
## "Q100010" "Q99716" "Q99581" "Q99480"
## Q98869 Q98578 Q98059 Q98078
## "Q98869" "Q98578" "Q98059" "Q98078"
## Q98197 Q96024 .src
## "Q98197" "Q96024" ".src"## label step_major step_minor label_minor bgn end
## 8 extract.features.string 2 5 5 11.512 11.568
## 9 extract.features.end 2 6 6 11.569 NA
## elapsed
## 8 0.056
## 9 NAStep 2.6: extract features end
## time trans "bgn " "fit.data.training.all " "predict.data.new " "end "
## 0.0000 multiple enabled transitions: data.training.all data.new model.selected firing: data.training.all
## 1.0000 1 2 1 0 0
## 1.0000 multiple enabled transitions: data.training.all data.new model.selected model.final data.training.all.prediction firing: data.new
## 2.0000 2 1 1 1 0
## label step_major step_minor label_minor bgn end
## 9 extract.features.end 2 6 6 11.569 12.244
## 10 manage.missing.data 3 0 0 12.245 NA
## elapsed
## 9 0.675
## 10 NAStep 3.0: manage missing data
## [1] "numeric data missing in : "
## YOB Party.fctr
## 128 622
## [1] "numeric data w/ 0s in : "
## YOB.Age.dff
## 136
## [1] "numeric data w/ Infs in : "
## named integer(0)
## [1] "numeric data w/ NaNs in : "
## named integer(0)
## [1] "string data missing in : "
## Gender Income HouseholdStatus EducationLevel
## 46 445 177 410
## Party Q124742 Q124122 Q123464
## NA 1438 823 708
## Q123621 Q122769 Q122770 Q122771
## 778 644 594 587
## Q122120 Q121699 Q121700 Q120978
## 585 547 563 599
## Q121011 Q120379 Q120650 Q120472
## 571 607 655 649
## Q120194 Q120012 Q120014 Q119334
## 654 591 641 568
## Q119851 Q119650 Q118892 Q118117
## 540 578 486 479
## Q118232 Q118233 Q118237 Q117186
## 701 554 539 648
## Q117193 Q116797 Q116881 Q116953
## 655 590 635 616
## Q116601 Q116441 Q116448 Q116197
## 534 541 560 551
## Q115602 Q115777 Q115610 Q115611
## 539 578 537 487
## Q115899 Q115390 Q114961 Q114748
## 573 619 538 447
## Q115195 Q114517 Q114386 Q113992
## 525 481 521 447
## Q114152 Q113583 Q113584 Q113181
## 537 514 512 453
## Q112478 Q112512 Q112270 Q111848
## 494 460 521 398
## Q111580 Q111220 Q110740 Q109367
## 474 379 357 168
## Q108950 Q109244 Q108855 Q108617
## 204 0 438 288
## Q108856 Q108754 Q108342 Q108343
## 436 338 341 333
## Q107869 Q107491 Q106993 Q106997
## 389 366 389 396
## Q106272 Q106388 Q106389 Q106042
## 426 476 495 451
## Q105840 Q105655 Q104996 Q103293
## 487 393 400 431
## Q102906 Q102674 Q102687 Q102289
## 493 511 475 484
## Q102089 Q101162 Q101163 Q101596
## 462 498 572 477
## Q100689 Q100680 Q100562 Q99982
## 414 497 487 514
## Q100010 Q99716 Q99581 Q99480
## 445 500 466 478
## Q98869 Q98578 Q98059 Q98078
## 564 542 450 569
## Q98197 Q96024
## 528 550## [1] "numeric data missing in : "
## YOB Party.fctr
## 128 622
## [1] "numeric data w/ 0s in : "
## YOB.Age.dff
## 136
## [1] "numeric data w/ Infs in : "
## named integer(0)
## [1] "numeric data w/ NaNs in : "
## named integer(0)
## [1] "string data missing in : "
## Gender Income HouseholdStatus EducationLevel
## 46 445 177 410
## Party Q124742 Q124122 Q123464
## NA 1438 823 708
## Q123621 Q122769 Q122770 Q122771
## 778 644 594 587
## Q122120 Q121699 Q121700 Q120978
## 585 547 563 599
## Q121011 Q120379 Q120650 Q120472
## 571 607 655 649
## Q120194 Q120012 Q120014 Q119334
## 654 591 641 568
## Q119851 Q119650 Q118892 Q118117
## 540 578 486 479
## Q118232 Q118233 Q118237 Q117186
## 701 554 539 648
## Q117193 Q116797 Q116881 Q116953
## 655 590 635 616
## Q116601 Q116441 Q116448 Q116197
## 534 541 560 551
## Q115602 Q115777 Q115610 Q115611
## 539 578 537 487
## Q115899 Q115390 Q114961 Q114748
## 573 619 538 447
## Q115195 Q114517 Q114386 Q113992
## 525 481 521 447
## Q114152 Q113583 Q113584 Q113181
## 537 514 512 453
## Q112478 Q112512 Q112270 Q111848
## 494 460 521 398
## Q111580 Q111220 Q110740 Q109367
## 474 379 357 168
## Q108950 Q109244 Q108855 Q108617
## 204 0 438 288
## Q108856 Q108754 Q108342 Q108343
## 436 338 341 333
## Q107869 Q107491 Q106993 Q106997
## 389 366 389 396
## Q106272 Q106388 Q106389 Q106042
## 426 476 495 451
## Q105840 Q105655 Q104996 Q103293
## 487 393 400 431
## Q102906 Q102674 Q102687 Q102289
## 493 511 475 484
## Q102089 Q101162 Q101163 Q101596
## 462 498 572 477
## Q100689 Q100680 Q100562 Q99982
## 414 497 487 514
## Q100010 Q99716 Q99581 Q99480
## 445 500 466 478
## Q98869 Q98578 Q98059 Q98078
## 564 542 450 569
## Q98197 Q96024
## 528 550## label step_major step_minor label_minor bgn end
## 10 manage.missing.data 3 0 0 12.245 12.802
## 11 cluster.data 4 0 0 12.802 NA
## elapsed
## 10 0.557
## 11 NAStep 4.0: cluster data
```{r cluster.data, cache=FALSE, echo=FALSE, eval=myevlChunk(glbChunks, glbOut$pfx)}
## Loading required package: proxy##
## Attaching package: 'proxy'## The following objects are masked from 'package:stats':
##
## as.dist, dist## The following object is masked from 'package:base':
##
## as.matrix## Loading required package: dynamicTreeCut## Loading required package: entropy## Loading required package: tidyr## Loading required package: ggdendro## [1] "Clustering features: "## Warning in cor(data.matrix(glbObsAll[glbObsAll$.src == "Train",
## glbFeatsCluster]), : the standard deviation is zero## abs.cor.y
## Q108855.fctr 0.05525571
## Q116881.fctr 0.05625959
## Q98197.fctr 0.07400689
## Q113181.fctr 0.09842608
## Q115611.fctr 0.10612270
## [1] " .rnorm cor: -0.0049"
## [1] " Clustering entropy measure: Party.fctr"
## [1] "glbObsAll Entropy: 0.6810"## Loading required package: lazyeval## Hhold.fctr .clusterid Hhold.fctr.clusterid D R .entropy .knt
## 1 N 1 N_1 59 85 0.6767573 144
## 2 MKn 1 MKn_1 123 178 0.6763589 301
## 3 MKy 1 MKy_1 306 530 0.6568082 836
## 4 PKn 1 PKn_1 40 23 0.6562848 63
## 5 PKy 1 PKy_1 13 7 0.6474466 20
## 6 SKn 1 SKn_1 454 557 0.6879485 1011
## 7 SKy 1 SKy_1 43 41 0.6928637 84
## [1] "glbObsAll$Hhold.fctr Entropy: 0.6743 (99.0230 pct)"## [1] "Category: N"
## [1] "max distance(0.9762) pair:"
## USER_ID Party.fctr Hhold.fctr Q124742.fctr Q124122.fctr Q123621.fctr
## 1315 1632 D N No No No
## 3744 4667 R N NA NA NA
## Q123464.fctr Q122771.fctr Q122770.fctr Q122769.fctr Q122120.fctr
## 1315 No Pc NA NA NA
## 3744 NA NA NA NA Yes
## Q121700.fctr Q121699.fctr Q121011.fctr Q120978.fctr Q120650.fctr
## 1315 No Yes Yes NA NA
## 3744 NA NA NA Yes NA
## Q120472.fctr Q120379.fctr Q120194.fctr Q120014.fctr Q120012.fctr
## 1315 NA No NA No Yes
## 3744 Science NA NA NA Yes
## Q119851.fctr Q119650.fctr Q119334.fctr Q118892.fctr Q118237.fctr
## 1315 No Receiving NA Yes Yes
## 3744 Yes NA NA NA No
## Q118233.fctr Q118232.fctr Q118117.fctr Q117193.fctr Q117186.fctr
## 1315 No NA Yes Odd hours NA
## 3744 NA NA Yes NA Hot headed
## Q116797.fctr Q116881.fctr Q116953.fctr Q116601.fctr Q116441.fctr
## 1315 NA NA Yes No NA
## 3744 NA Right No NA NA
## Q116448.fctr Q116197.fctr Q115602.fctr Q115777.fctr Q115610.fctr
## 1315 No NA NA NA NA
## 3744 NA P.M. NA Start NA
## Q115611.fctr Q115899.fctr Q115390.fctr Q115195.fctr Q114961.fctr
## 1315 NA NA NA Yes NA
## 3744 NA NA Yes NA NA
## Q114748.fctr Q114517.fctr Q114386.fctr Q114152.fctr Q113992.fctr
## 1315 NA NA NA NA NA
## 3744 NA NA NA NA NA
## Q113583.fctr Q113584.fctr Q113181.fctr Q112478.fctr Q112512.fctr
## 1315 Tunes People NA Yes NA
## 3744 NA NA NA Yes Yes
## Q112270.fctr Q111848.fctr Q111580.fctr Q111220.fctr Q110740.fctr
## 1315 Yes Yes Supportive No NA
## 3744 Yes NA NA No PC
## Q109367.fctr Q109244.fctr Q108950.fctr Q108855.fctr Q108617.fctr
## 1315 No No Cautious NA NA
## 3744 NA No NA NA NA
## Q108856.fctr Q108754.fctr Q108342.fctr Q108343.fctr Q107869.fctr
## 1315 NA No In-person NA No
## 3744 NA NA In-person NA NA
## Q107491.fctr Q106993.fctr Q106997.fctr Q106272.fctr Q106388.fctr
## 1315 Yes NA NA NA NA
## 3744 NA NA NA NA NA
## Q106389.fctr Q106042.fctr Q105840.fctr Q105655.fctr Q104996.fctr
## 1315 NA No NA Yes No
## 3744 NA NA NA Yes NA
## Q103293.fctr Q102906.fctr Q102674.fctr Q102687.fctr Q102289.fctr
## 1315 No No No Yes No
## 3744 NA NA NA NA NA
## Q102089.fctr Q101162.fctr Q101163.fctr Q101596.fctr Q100689.fctr
## 1315 NA Optimist NA No No
## 3744 NA Optimist Mom NA NA
## Q100680.fctr Q100562.fctr Q100010.fctr Q99982.fctr Q99716.fctr
## 1315 No NA No NA No
## 3744 No Yes NA NA NA
## Q99581.fctr Q99480.fctr Q98869.fctr Q98578.fctr Q98197.fctr
## 1315 No Yes NA Yes NA
## 3744 NA NA Yes Yes NA
## Q98059.fctr Q98078.fctr Q96024.fctr
## 1315 Yes NA NA
## 3744 NA NA NA
## [1] "min distance(0.9567) pair:"
## USER_ID Party.fctr Hhold.fctr Q124742.fctr Q124122.fctr Q123621.fctr
## 4256 5305 R N NA NA NA
## 4775 5956 R N NA NA NA
## Q123464.fctr Q122771.fctr Q122770.fctr Q122769.fctr Q122120.fctr
## 4256 NA NA NA NA NA
## 4775 NA NA NA NA NA
## Q121700.fctr Q121699.fctr Q121011.fctr Q120978.fctr Q120650.fctr
## 4256 NA NA NA NA NA
## 4775 NA NA NA NA NA
## Q120472.fctr Q120379.fctr Q120194.fctr Q120014.fctr Q120012.fctr
## 4256 NA NA NA NA NA
## 4775 NA NA NA NA NA
## Q119851.fctr Q119650.fctr Q119334.fctr Q118892.fctr Q118237.fctr
## 4256 NA NA NA NA NA
## 4775 NA NA NA NA NA
## Q118233.fctr Q118232.fctr Q118117.fctr Q117193.fctr Q117186.fctr
## 4256 NA NA NA NA NA
## 4775 NA NA NA Standard hours Cool headed
## Q116797.fctr Q116881.fctr Q116953.fctr Q116601.fctr Q116441.fctr
## 4256 NA NA NA No No
## 4775 No Right Yes Yes No
## Q116448.fctr Q116197.fctr Q115602.fctr Q115777.fctr Q115610.fctr
## 4256 Yes P.M. Yes End Yes
## 4775 No P.M. Yes Start Yes
## Q115611.fctr Q115899.fctr Q115390.fctr Q115195.fctr Q114961.fctr
## 4256 Yes Me Yes Yes Yes
## 4775 Yes Cs No No No
## Q114748.fctr Q114517.fctr Q114386.fctr Q114152.fctr Q113992.fctr
## 4256 Yes No TMI No NA
## 4775 Yes No Mysterious Yes No
## Q113583.fctr Q113584.fctr Q113181.fctr Q112478.fctr Q112512.fctr
## 4256 NA NA Yes NA NA
## 4775 Tunes People Yes Yes Yes
## Q112270.fctr Q111848.fctr Q111580.fctr Q111220.fctr Q110740.fctr
## 4256 NA NA NA No Mac
## 4775 Yes Yes Supportive No Mac
## Q109367.fctr Q109244.fctr Q108950.fctr Q108855.fctr Q108617.fctr
## 4256 Yes No Risk-friendly Umm... No
## 4775 No No Cautious Yes! No
## Q108856.fctr Q108754.fctr Q108342.fctr Q108343.fctr Q107869.fctr
## 4256 Socialize Yes NA NA No
## 4775 Space No In-person No No
## Q107491.fctr Q106993.fctr Q106997.fctr Q106272.fctr Q106388.fctr
## 4256 Yes No Yy Yes No
## 4775 Yes Yes Yy Yes No
## Q106389.fctr Q106042.fctr Q105840.fctr Q105655.fctr Q104996.fctr
## 4256 No No No Yes Yes
## 4775 No Yes No Yes Yes
## Q103293.fctr Q102906.fctr Q102674.fctr Q102687.fctr Q102289.fctr
## 4256 Yes Yes No Yes No
## 4775 Yes No No Yes No
## Q102089.fctr Q101162.fctr Q101163.fctr Q101596.fctr Q100689.fctr
## 4256 Own Optimist Dad No No
## 4775 Own Optimist Dad Yes No
## Q100680.fctr Q100562.fctr Q100010.fctr Q99982.fctr Q99716.fctr
## 4256 Yes Yes No Nope NA
## 4775 No Yes No Nope No
## Q99581.fctr Q99480.fctr Q98869.fctr Q98578.fctr Q98197.fctr
## 4256 NA NA Yes Yes Yes
## 4775 Yes Yes Yes Yes Yes
## Q98059.fctr Q98078.fctr Q96024.fctr
## 4256 Yes Yes NA
## 4775 Yes Yes NA
## [1] "Category: MKn"
## [1] "max distance(0.9764) pair:"
## USER_ID Party.fctr Hhold.fctr Q124742.fctr Q124122.fctr Q123621.fctr
## 2961 3680 R MKn NA NA Yes
## 4750 5926 R MKn NA NA NA
## Q123464.fctr Q122771.fctr Q122770.fctr Q122769.fctr Q122120.fctr
## 2961 No Pt Yes No No
## 4750 NA NA NA NA NA
## Q121700.fctr Q121699.fctr Q121011.fctr Q120978.fctr Q120650.fctr
## 2961 No Yes Yes Yes Yes
## 4750 NA NA NA NA NA
## Q120472.fctr Q120379.fctr Q120194.fctr Q120014.fctr Q120012.fctr
## 2961 Science Yes NA Yes Yes
## 4750 NA NA NA NA NA
## Q119851.fctr Q119650.fctr Q119334.fctr Q118892.fctr Q118237.fctr
## 2961 No Giving No Yes Yes
## 4750 NA NA NA NA Yes
## Q118233.fctr Q118232.fctr Q118117.fctr Q117193.fctr Q117186.fctr
## 2961 No Pr No Standard hours Hot headed
## 4750 Yes Pr Yes NA NA
## Q116797.fctr Q116881.fctr Q116953.fctr Q116601.fctr Q116441.fctr
## 2961 NA NA NA NA NA
## 4750 NA NA NA Yes Yes
## Q116448.fctr Q116197.fctr Q115602.fctr Q115777.fctr Q115610.fctr
## 2961 NA NA NA Start NA
## 4750 No NA NA NA NA
## Q115611.fctr Q115899.fctr Q115390.fctr Q115195.fctr Q114961.fctr
## 2961 NA NA NA NA NA
## 4750 NA NA NA Yes Yes
## Q114748.fctr Q114517.fctr Q114386.fctr Q114152.fctr Q113992.fctr
## 2961 NA NA NA NA NA
## 4750 Yes Yes Mysterious NA No
## Q113583.fctr Q113584.fctr Q113181.fctr Q112478.fctr Q112512.fctr
## 2961 NA NA NA NA NA
## 4750 Tunes Technology NA No NA
## Q112270.fctr Q111848.fctr Q111580.fctr Q111220.fctr Q110740.fctr
## 2961 NA NA NA NA NA
## 4750 No Yes Supportive No PC
## Q109367.fctr Q109244.fctr Q108950.fctr Q108855.fctr Q108617.fctr
## 2961 No No Cautious Umm... No
## 4750 Yes No Cautious Umm... No
## Q108856.fctr Q108754.fctr Q108342.fctr Q108343.fctr Q107869.fctr
## 2961 Space Yes Online No No
## 4750 Space No In-person No NA
## Q107491.fctr Q106993.fctr Q106997.fctr Q106272.fctr Q106388.fctr
## 2961 Yes Yes Gr NA NA
## 4750 No No Gr Yes Yes
## Q106389.fctr Q106042.fctr Q105840.fctr Q105655.fctr Q104996.fctr
## 2961 NA NA NA NA NA
## 4750 Yes No No Yes Yes
## Q103293.fctr Q102906.fctr Q102674.fctr Q102687.fctr Q102289.fctr
## 2961 NA NA NA NA NA
## 4750 No No Yes Yes Yes
## Q102089.fctr Q101162.fctr Q101163.fctr Q101596.fctr Q100689.fctr
## 2961 NA NA NA NA NA
## 4750 Own Optimist Dad Yes No
## Q100680.fctr Q100562.fctr Q100010.fctr Q99982.fctr Q99716.fctr
## 2961 NA NA NA NA NA
## 4750 Yes Yes Yes Nope No
## Q99581.fctr Q99480.fctr Q98869.fctr Q98578.fctr Q98197.fctr
## 2961 NA NA NA NA NA
## 4750 No Yes Yes Yes Yes
## Q98059.fctr Q98078.fctr Q96024.fctr
## 2961 NA NA NA
## 4750 Yes Yes No
## [1] "min distance(0.9562) pair:"
## USER_ID Party.fctr Hhold.fctr Q124742.fctr Q124122.fctr Q123621.fctr
## 4260 5310 R MKn NA NA NA
## 6399 4226 <NA> MKn NA NA NA
## Q123464.fctr Q122771.fctr Q122770.fctr Q122769.fctr Q122120.fctr
## 4260 NA Pt Yes NA NA
## 6399 NA NA NA NA NA
## Q121700.fctr Q121699.fctr Q121011.fctr Q120978.fctr Q120650.fctr
## 4260 NA NA Yes Yes NA
## 6399 NA NA NA NA NA
## Q120472.fctr Q120379.fctr Q120194.fctr Q120014.fctr Q120012.fctr
## 4260 NA NA NA NA NA
## 6399 NA No Try first Yes No
## Q119851.fctr Q119650.fctr Q119334.fctr Q118892.fctr Q118237.fctr
## 4260 NA NA NA NA NA
## 6399 Yes Giving No NA NA
## Q118233.fctr Q118232.fctr Q118117.fctr Q117193.fctr Q117186.fctr
## 4260 NA NA NA Standard hours Cool headed
## 6399 NA NA Yes Standard hours NA
## Q116797.fctr Q116881.fctr Q116953.fctr Q116601.fctr Q116441.fctr
## 4260 No Right No Yes No
## 6399 No Right Yes Yes No
## Q116448.fctr Q116197.fctr Q115602.fctr Q115777.fctr Q115610.fctr
## 4260 Yes P.M. No Start Yes
## 6399 Yes A.M. NA End NA
## Q115611.fctr Q115899.fctr Q115390.fctr Q115195.fctr Q114961.fctr
## 4260 Yes Me No Yes Yes
## 6399 Yes Me NA NA NA
## Q114748.fctr Q114517.fctr Q114386.fctr Q114152.fctr Q113992.fctr
## 4260 NA NA NA NA No
## 6399 Yes Yes Mysterious No No
## Q113583.fctr Q113584.fctr Q113181.fctr Q112478.fctr Q112512.fctr
## 4260 Talk People Yes NA Yes
## 6399 Talk Technology Yes No Yes
## Q112270.fctr Q111848.fctr Q111580.fctr Q111220.fctr Q110740.fctr
## 4260 NA No NA NA PC
## 6399 No NA NA No PC
## Q109367.fctr Q109244.fctr Q108950.fctr Q108855.fctr Q108617.fctr
## 4260 Yes No Risk-friendly Yes! No
## 6399 Yes No Cautious NA NA
## Q108856.fctr Q108754.fctr Q108342.fctr Q108343.fctr Q107869.fctr
## 4260 Space Yes NA NA NA
## 6399 NA NA NA NA NA
## Q107491.fctr Q106993.fctr Q106997.fctr Q106272.fctr Q106388.fctr
## 4260 NA NA NA NA NA
## 6399 NA Yes Gr NA NA
## Q106389.fctr Q106042.fctr Q105840.fctr Q105655.fctr Q104996.fctr
## 4260 NA NA NA NA NA
## 6399 NA NA NA NA No
## Q103293.fctr Q102906.fctr Q102674.fctr Q102687.fctr Q102289.fctr
## 4260 NA NA NA NA NA
## 6399 NA NA NA NA NA
## Q102089.fctr Q101162.fctr Q101163.fctr Q101596.fctr Q100689.fctr
## 4260 Rent Optimist Mom Yes NA
## 6399 Own Optimist Dad No Yes
## Q100680.fctr Q100562.fctr Q100010.fctr Q99982.fctr Q99716.fctr
## 4260 NA NA NA NA No
## 6399 NA NA NA NA No
## Q99581.fctr Q99480.fctr Q98869.fctr Q98578.fctr Q98197.fctr
## 4260 No Yes NA NA NA
## 6399 Yes No Yes No NA
## Q98059.fctr Q98078.fctr Q96024.fctr
## 4260 NA NA Yes
## 6399 NA NA NA
## [1] "Category: MKy"
## [1] "max distance(0.9760) pair:"
## USER_ID Party.fctr Hhold.fctr Q124742.fctr Q124122.fctr Q123621.fctr
## 1198 1481 R MKy NA NA NA
## 4133 5153 D MKy NA NA NA
## Q123464.fctr Q122771.fctr Q122770.fctr Q122769.fctr Q122120.fctr
## 1198 NA NA NA NA NA
## 4133 NA Pc Yes No Yes
## Q121700.fctr Q121699.fctr Q121011.fctr Q120978.fctr Q120650.fctr
## 1198 No Yes Yes Yes Yes
## 4133 Yes Yes Yes NA NA
## Q120472.fctr Q120379.fctr Q120194.fctr Q120014.fctr Q120012.fctr
## 1198 NA No NA NA NA
## 4133 Art Yes NA NA NA
## Q119851.fctr Q119650.fctr Q119334.fctr Q118892.fctr Q118237.fctr
## 1198 NA NA No No NA
## 4133 NA NA No Yes Yes
## Q118233.fctr Q118232.fctr Q118117.fctr Q117193.fctr Q117186.fctr
## 1198 NA NA NA NA NA
## 4133 No Id Yes Odd hours Cool headed
## Q116797.fctr Q116881.fctr Q116953.fctr Q116601.fctr Q116441.fctr
## 1198 NA NA NA NA NA
## 4133 No Happy No NA NA
## Q116448.fctr Q116197.fctr Q115602.fctr Q115777.fctr Q115610.fctr
## 1198 NA NA NA NA NA
## 4133 NA NA NA NA NA
## Q115611.fctr Q115899.fctr Q115390.fctr Q115195.fctr Q114961.fctr
## 1198 NA NA NA NA NA
## 4133 NA NA NA NA NA
## Q114748.fctr Q114517.fctr Q114386.fctr Q114152.fctr Q113992.fctr
## 1198 NA NA NA NA NA
## 4133 NA NA NA NA NA
## Q113583.fctr Q113584.fctr Q113181.fctr Q112478.fctr Q112512.fctr
## 1198 NA NA NA NA NA
## 4133 NA NA NA NA NA
## Q112270.fctr Q111848.fctr Q111580.fctr Q111220.fctr Q110740.fctr
## 1198 NA NA NA NA NA
## 4133 Yes No Demanding Yes Mac
## Q109367.fctr Q109244.fctr Q108950.fctr Q108855.fctr Q108617.fctr
## 1198 NA No Cautious NA NA
## 4133 Yes No Risk-friendly Yes! Yes
## Q108856.fctr Q108754.fctr Q108342.fctr Q108343.fctr Q107869.fctr
## 1198 NA NA NA NA No
## 4133 Space No Online Yes Yes
## Q107491.fctr Q106993.fctr Q106997.fctr Q106272.fctr Q106388.fctr
## 1198 Yes Yes Gr No No
## 4133 Yes No Yy NA NA
## Q106389.fctr Q106042.fctr Q105840.fctr Q105655.fctr Q104996.fctr
## 1198 No No Yes No NA
## 4133 NA NA NA NA NA
## Q103293.fctr Q102906.fctr Q102674.fctr Q102687.fctr Q102289.fctr
## 1198 NA NA Yes No No
## 4133 No No Yes No Yes
## Q102089.fctr Q101162.fctr Q101163.fctr Q101596.fctr Q100689.fctr
## 1198 Own Optimist Mom Yes Yes
## 4133 Rent NA NA NA NA
## Q100680.fctr Q100562.fctr Q100010.fctr Q99982.fctr Q99716.fctr
## 1198 Yes Yes Yes Nope No
## 4133 NA NA NA NA NA
## Q99581.fctr Q99480.fctr Q98869.fctr Q98578.fctr Q98197.fctr
## 1198 No No NA NA NA
## 4133 NA NA NA NA NA
## Q98059.fctr Q98078.fctr Q96024.fctr
## 1198 Yes No No
## 4133 NA NA NA
## [1] "min distance(0.9501) pair:"
## USER_ID Party.fctr Hhold.fctr Q124742.fctr Q124122.fctr Q123621.fctr
## 4299 5365 R MKy NA NA NA
## 6802 6188 <NA> MKy NA NA NA
## Q123464.fctr Q122771.fctr Q122770.fctr Q122769.fctr Q122120.fctr
## 4299 NA NA NA NA NA
## 6802 NA NA NA NA NA
## Q121700.fctr Q121699.fctr Q121011.fctr Q120978.fctr Q120650.fctr
## 4299 NA NA NA NA NA
## 6802 NA NA NA NA NA
## Q120472.fctr Q120379.fctr Q120194.fctr Q120014.fctr Q120012.fctr
## 4299 NA NA NA NA NA
## 6802 NA NA NA NA NA
## Q119851.fctr Q119650.fctr Q119334.fctr Q118892.fctr Q118237.fctr
## 4299 NA NA NA NA NA
## 6802 NA NA NA NA NA
## Q118233.fctr Q118232.fctr Q118117.fctr Q117193.fctr Q117186.fctr
## 4299 NA NA NA NA NA
## 6802 NA NA NA NA NA
## Q116797.fctr Q116881.fctr Q116953.fctr Q116601.fctr Q116441.fctr
## 4299 NA NA NA NA NA
## 6802 NA NA NA NA NA
## Q116448.fctr Q116197.fctr Q115602.fctr Q115777.fctr Q115610.fctr
## 4299 NA NA Yes NA Yes
## 6802 NA NA Yes End Yes
## Q115611.fctr Q115899.fctr Q115390.fctr Q115195.fctr Q114961.fctr
## 4299 Yes NA Yes Yes No
## 6802 Yes NA Yes Yes NA
## Q114748.fctr Q114517.fctr Q114386.fctr Q114152.fctr Q113992.fctr
## 4299 No Yes Mysterious Yes No
## 6802 No No Mysterious No Yes
## Q113583.fctr Q113584.fctr Q113181.fctr Q112478.fctr Q112512.fctr
## 4299 Talk People Yes NA NA
## 6802 NA Technology No NA NA
## Q112270.fctr Q111848.fctr Q111580.fctr Q111220.fctr Q110740.fctr
## 4299 NA NA NA NA NA
## 6802 NA NA NA NA NA
## Q109367.fctr Q109244.fctr Q108950.fctr Q108855.fctr Q108617.fctr
## 4299 Yes No NA NA NA
## 6802 Yes No Risk-friendly Umm... No
## Q108856.fctr Q108754.fctr Q108342.fctr Q108343.fctr Q107869.fctr
## 4299 NA NA NA NA NA
## 6802 Space Yes In-person Yes No
## Q107491.fctr Q106993.fctr Q106997.fctr Q106272.fctr Q106388.fctr
## 4299 NA NA NA NA NA
## 6802 Yes Yes Yy NA NA
## Q106389.fctr Q106042.fctr Q105840.fctr Q105655.fctr Q104996.fctr
## 4299 NA NA NA NA NA
## 6802 NA NA NA NA NA
## Q103293.fctr Q102906.fctr Q102674.fctr Q102687.fctr Q102289.fctr
## 4299 NA NA NA NA NA
## 6802 NA NA NA NA NA
## Q102089.fctr Q101162.fctr Q101163.fctr Q101596.fctr Q100689.fctr
## 4299 NA NA NA NA NA
## 6802 NA NA NA NA NA
## Q100680.fctr Q100562.fctr Q100010.fctr Q99982.fctr Q99716.fctr
## 4299 NA NA NA NA NA
## 6802 NA NA NA NA NA
## Q99581.fctr Q99480.fctr Q98869.fctr Q98578.fctr Q98197.fctr
## 4299 NA NA NA NA NA
## 6802 NA NA NA NA NA
## Q98059.fctr Q98078.fctr Q96024.fctr
## 4299 NA NA NA
## 6802 NA NA NA
## [1] "Category: PKn"
## [1] "max distance(0.9748) pair:"
## USER_ID Party.fctr Hhold.fctr Q124742.fctr Q124122.fctr Q123621.fctr
## 4183 5219 D PKn NA NA NA
## 6176 3074 <NA> PKn No Yes Yes
## Q123464.fctr Q122771.fctr Q122770.fctr Q122769.fctr Q122120.fctr
## 4183 NA NA NA NA NA
## 6176 No Pc Yes No No
## Q121700.fctr Q121699.fctr Q121011.fctr Q120978.fctr Q120650.fctr
## 4183 NA NA NA NA NA
## 6176 No Yes No No Yes
## Q120472.fctr Q120379.fctr Q120194.fctr Q120014.fctr Q120012.fctr
## 4183 NA NA NA NA NA
## 6176 Science No Study first Yes No
## Q119851.fctr Q119650.fctr Q119334.fctr Q118892.fctr Q118237.fctr
## 4183 NA NA NA NA NA
## 6176 Yes Giving No Yes No
## Q118233.fctr Q118232.fctr Q118117.fctr Q117193.fctr Q117186.fctr
## 4183 NA NA NA NA NA
## 6176 No Pr No Standard hours Cool headed
## Q116797.fctr Q116881.fctr Q116953.fctr Q116601.fctr Q116441.fctr
## 4183 NA NA NA NA NA
## 6176 Yes Right No Yes Yes
## Q116448.fctr Q116197.fctr Q115602.fctr Q115777.fctr Q115610.fctr
## 4183 NA NA NA NA NA
## 6176 No NA NA NA NA
## Q115611.fctr Q115899.fctr Q115390.fctr Q115195.fctr Q114961.fctr
## 4183 NA NA NA NA NA
## 6176 NA NA NA NA NA
## Q114748.fctr Q114517.fctr Q114386.fctr Q114152.fctr Q113992.fctr
## 4183 Yes No TMI No Yes
## 6176 NA NA NA NA NA
## Q113583.fctr Q113584.fctr Q113181.fctr Q112478.fctr Q112512.fctr
## 4183 NA NA NA NA NA
## 6176 NA NA NA NA NA
## Q112270.fctr Q111848.fctr Q111580.fctr Q111220.fctr Q110740.fctr
## 4183 NA NA Demanding No Mac
## 6176 NA NA NA NA NA
## Q109367.fctr Q109244.fctr Q108950.fctr Q108855.fctr Q108617.fctr
## 4183 Yes No Cautious Umm... No
## 6176 Yes No Cautious Umm... No
## Q108856.fctr Q108754.fctr Q108342.fctr Q108343.fctr Q107869.fctr
## 4183 Socialize No In-person Yes Yes
## 6176 Space Yes In-person No Yes
## Q107491.fctr Q106993.fctr Q106997.fctr Q106272.fctr Q106388.fctr
## 4183 Yes Yes NA No No
## 6176 Yes Yes Gr Yes No
## Q106389.fctr Q106042.fctr Q105840.fctr Q105655.fctr Q104996.fctr
## 4183 No No Yes No No
## 6176 Yes No No Yes NA
## Q103293.fctr Q102906.fctr Q102674.fctr Q102687.fctr Q102289.fctr
## 4183 Yes Yes NA NA No
## 6176 NA NA NA NA NA
## Q102089.fctr Q101162.fctr Q101163.fctr Q101596.fctr Q100689.fctr
## 4183 Rent Optimist Mom Yes Yes
## 6176 NA NA NA NA NA
## Q100680.fctr Q100562.fctr Q100010.fctr Q99982.fctr Q99716.fctr
## 4183 Yes Yes Yes Nope No
## 6176 NA NA NA NA NA
## Q99581.fctr Q99480.fctr Q98869.fctr Q98578.fctr Q98197.fctr
## 4183 No Yes Yes No No
## 6176 NA NA NA NA NA
## Q98059.fctr Q98078.fctr Q96024.fctr
## 4183 Yes No No
## 6176 NA NA NA
## [1] "min distance(0.9601) pair:"
## USER_ID Party.fctr Hhold.fctr Q124742.fctr Q124122.fctr Q123621.fctr
## 3970 4947 D PKn Yes Yes Yes
## 6428 4362 <NA> PKn Yes Yes Yes
## Q123464.fctr Q122771.fctr Q122770.fctr Q122769.fctr Q122120.fctr
## 3970 No Pc Yes Yes No
## 6428 No Pc Yes Yes No
## Q121700.fctr Q121699.fctr Q121011.fctr Q120978.fctr Q120650.fctr
## 3970 No Yes No Yes Yes
## 6428 No Yes No Yes Yes
## Q120472.fctr Q120379.fctr Q120194.fctr Q120014.fctr Q120012.fctr
## 3970 Science No Try first No Yes
## 6428 Science Yes Study first Yes No
## Q119851.fctr Q119650.fctr Q119334.fctr Q118892.fctr Q118237.fctr
## 3970 Yes Giving No Yes No
## 6428 Yes Giving Yes Yes No
## Q118233.fctr Q118232.fctr Q118117.fctr Q117193.fctr Q117186.fctr
## 3970 No Pr No Odd hours Cool headed
## 6428 Yes Id Yes Standard hours Hot headed
## Q116797.fctr Q116881.fctr Q116953.fctr Q116601.fctr Q116441.fctr
## 3970 No Happy No Yes No
## 6428 Yes Happy No Yes Yes
## Q116448.fctr Q116197.fctr Q115602.fctr Q115777.fctr Q115610.fctr
## 3970 Yes A.M. Yes End Yes
## 6428 Yes A.M. Yes Start Yes
## Q115611.fctr Q115899.fctr Q115390.fctr Q115195.fctr Q114961.fctr
## 3970 Yes Cs No No No
## 6428 Yes Cs Yes Yes Yes
## Q114748.fctr Q114517.fctr Q114386.fctr Q114152.fctr Q113992.fctr
## 3970 Yes No TMI No No
## 6428 Yes Yes Mysterious Yes No
## Q113583.fctr Q113584.fctr Q113181.fctr Q112478.fctr Q112512.fctr
## 3970 Tunes People Yes No Yes
## 6428 Talk People Yes Yes No
## Q112270.fctr Q111848.fctr Q111580.fctr Q111220.fctr Q110740.fctr
## 3970 Yes Yes Demanding No PC
## 6428 Yes Yes Supportive No PC
## Q109367.fctr Q109244.fctr Q108950.fctr Q108855.fctr Q108617.fctr
## 3970 Yes No Cautious Umm... No
## 6428 No No Cautious Yes! No
## Q108856.fctr Q108754.fctr Q108342.fctr Q108343.fctr Q107869.fctr
## 3970 Space No In-person No Yes
## 6428 Space Yes In-person No Yes
## Q107491.fctr Q106993.fctr Q106997.fctr Q106272.fctr Q106388.fctr
## 3970 Yes Yes Gr Yes No
## 6428 Yes Yes Gr Yes No
## Q106389.fctr Q106042.fctr Q105840.fctr Q105655.fctr Q104996.fctr
## 3970 No Yes Yes No Yes
## 6428 Yes Yes No No Yes
## Q103293.fctr Q102906.fctr Q102674.fctr Q102687.fctr Q102289.fctr
## 3970 Yes Yes Yes No No
## 6428 Yes Yes No Yes No
## Q102089.fctr Q101162.fctr Q101163.fctr Q101596.fctr Q100689.fctr
## 3970 Own Optimist Dad No Yes
## 6428 Own Optimist Dad No No
## Q100680.fctr Q100562.fctr Q100010.fctr Q99982.fctr Q99716.fctr
## 3970 Yes Yes Yes Nope No
## 6428 Yes Yes Yes Check! No
## Q99581.fctr Q99480.fctr Q98869.fctr Q98578.fctr Q98197.fctr
## 3970 No Yes Yes No Yes
## 6428 No Yes Yes NA Yes
## Q98059.fctr Q98078.fctr Q96024.fctr
## 3970 Yes No No
## 6428 Yes No Yes
## [1] "Category: PKy"
## [1] "max distance(0.9743) pair:"
## USER_ID Party.fctr Hhold.fctr Q124742.fctr Q124122.fctr Q123621.fctr
## 1564 1937 R PKy NA NA NA
## 4351 5432 D PKy NA NA NA
## Q123464.fctr Q122771.fctr Q122770.fctr Q122769.fctr Q122120.fctr
## 1564 NA NA NA NA NA
## 4351 NA NA NA NA NA
## Q121700.fctr Q121699.fctr Q121011.fctr Q120978.fctr Q120650.fctr
## 1564 NA NA NA NA NA
## 4351 NA NA No Yes Yes
## Q120472.fctr Q120379.fctr Q120194.fctr Q120014.fctr Q120012.fctr
## 1564 NA NA NA NA NA
## 4351 Science No Try first No Yes
## Q119851.fctr Q119650.fctr Q119334.fctr Q118892.fctr Q118237.fctr
## 1564 No Giving No Yes Yes
## 4351 Yes Giving No Yes Yes
## Q118233.fctr Q118232.fctr Q118117.fctr Q117193.fctr Q117186.fctr
## 1564 No Id No Odd hours Cool headed
## 4351 No Id Yes NA NA
## Q116797.fctr Q116881.fctr Q116953.fctr Q116601.fctr Q116441.fctr
## 1564 No Happy Yes Yes Yes
## 4351 NA NA NA NA NA
## Q116448.fctr Q116197.fctr Q115602.fctr Q115777.fctr Q115610.fctr
## 1564 Yes NA NA NA NA
## 4351 NA NA NA NA NA
## Q115611.fctr Q115899.fctr Q115390.fctr Q115195.fctr Q114961.fctr
## 1564 NA NA NA NA NA
## 4351 NA NA NA NA NA
## Q114748.fctr Q114517.fctr Q114386.fctr Q114152.fctr Q113992.fctr
## 1564 NA NA NA NA NA
## 4351 NA NA NA NA NA
## Q113583.fctr Q113584.fctr Q113181.fctr Q112478.fctr Q112512.fctr
## 1564 NA NA NA NA NA
## 4351 NA NA NA NA NA
## Q112270.fctr Q111848.fctr Q111580.fctr Q111220.fctr Q110740.fctr
## 1564 NA Yes Demanding Yes PC
## 4351 NA NA NA NA NA
## Q109367.fctr Q109244.fctr Q108950.fctr Q108855.fctr Q108617.fctr
## 1564 Yes No NA NA NA
## 4351 No No Cautious Yes! Yes
## Q108856.fctr Q108754.fctr Q108342.fctr Q108343.fctr Q107869.fctr
## 1564 NA NA NA NA NA
## 4351 Space No NA NA No
## Q107491.fctr Q106993.fctr Q106997.fctr Q106272.fctr Q106388.fctr
## 1564 Yes No Gr Yes No
## 4351 Yes NA NA NA NA
## Q106389.fctr Q106042.fctr Q105840.fctr Q105655.fctr Q104996.fctr
## 1564 No No No No Yes
## 4351 NA NA NA NA NA
## Q103293.fctr Q102906.fctr Q102674.fctr Q102687.fctr Q102289.fctr
## 1564 Yes No NA NA NA
## 4351 NA NA NA NA NA
## Q102089.fctr Q101162.fctr Q101163.fctr Q101596.fctr Q100689.fctr
## 1564 Own Optimist Dad Yes No
## 4351 NA NA NA NA NA
## Q100680.fctr Q100562.fctr Q100010.fctr Q99982.fctr Q99716.fctr
## 1564 Yes Yes No Nope No
## 4351 NA NA NA NA NA
## Q99581.fctr Q99480.fctr Q98869.fctr Q98578.fctr Q98197.fctr
## 1564 No NA No Yes No
## 4351 No Yes NA NA NA
## Q98059.fctr Q98078.fctr Q96024.fctr
## 1564 Yes No Yes
## 4351 NA NA NA
## [1] "min distance(0.9619) pair:"
## USER_ID Party.fctr Hhold.fctr Q124742.fctr Q124122.fctr Q123621.fctr
## 719 891 D PKy Yes No Yes
## 1417 1762 D PKy Yes No Yes
## Q123464.fctr Q122771.fctr Q122770.fctr Q122769.fctr Q122120.fctr
## 719 No Pt No No No
## 1417 No Pt No Yes No
## Q121700.fctr Q121699.fctr Q121011.fctr Q120978.fctr Q120650.fctr
## 719 No Yes No Yes Yes
## 1417 No Yes Yes Yes Yes
## Q120472.fctr Q120379.fctr Q120194.fctr Q120014.fctr Q120012.fctr
## 719 Science No Study first Yes No
## 1417 Science No Study first Yes No
## Q119851.fctr Q119650.fctr Q119334.fctr Q118892.fctr Q118237.fctr
## 719 No Giving No No Yes
## 1417 No Giving Yes No Yes
## Q118233.fctr Q118232.fctr Q118117.fctr Q117193.fctr Q117186.fctr
## 719 Yes Id No Odd hours Hot headed
## 1417 Yes Pr Yes Odd hours Cool headed
## Q116797.fctr Q116881.fctr Q116953.fctr Q116601.fctr Q116441.fctr
## 719 No Happy No No Yes
## 1417 Yes Happy Yes Yes Yes
## Q116448.fctr Q116197.fctr Q115602.fctr Q115777.fctr Q115610.fctr
## 719 No P.M. Yes Start No
## 1417 No A.M. Yes Start Yes
## Q115611.fctr Q115899.fctr Q115390.fctr Q115195.fctr Q114961.fctr
## 719 Yes Cs Yes Yes No
## 1417 Yes Me Yes No No
## Q114748.fctr Q114517.fctr Q114386.fctr Q114152.fctr Q113992.fctr
## 719 No Yes Mysterious No Yes
## 1417 Yes No Mysterious Yes Yes
## Q113583.fctr Q113584.fctr Q113181.fctr Q112478.fctr Q112512.fctr
## 719 Tunes People No No Yes
## 1417 Talk Technology Yes Yes Yes
## Q112270.fctr Q111848.fctr Q111580.fctr Q111220.fctr Q110740.fctr
## 719 Yes No Supportive No Mac
## 1417 Yes No Demanding No PC
## Q109367.fctr Q109244.fctr Q108950.fctr Q108855.fctr Q108617.fctr
## 719 Yes No Risk-friendly Yes! No
## 1417 Yes No Risk-friendly Umm... No
## Q108856.fctr Q108754.fctr Q108342.fctr Q108343.fctr Q107869.fctr
## 719 Socialize Yes In-person No Yes
## 1417 Socialize Yes In-person No Yes
## Q107491.fctr Q106993.fctr Q106997.fctr Q106272.fctr Q106388.fctr
## 719 Yes Yes Gr Yes Yes
## 1417 Yes No Yy No Yes
## Q106389.fctr Q106042.fctr Q105840.fctr Q105655.fctr Q104996.fctr
## 719 No No No Yes Yes
## 1417 Yes Yes Yes No Yes
## Q103293.fctr Q102906.fctr Q102674.fctr Q102687.fctr Q102289.fctr
## 719 Yes No Yes Yes No
## 1417 No No Yes Yes Yes
## Q102089.fctr Q101162.fctr Q101163.fctr Q101596.fctr Q100689.fctr
## 719 Own Optimist Mom No No
## 1417 Own Optimist Mom No Yes
## Q100680.fctr Q100562.fctr Q100010.fctr Q99982.fctr Q99716.fctr
## 719 No Yes Yes Nope No
## 1417 Yes Yes Yes Check! No
## Q99581.fctr Q99480.fctr Q98869.fctr Q98578.fctr Q98197.fctr
## 719 No No Yes No No
## 1417 No Yes Yes No Yes
## Q98059.fctr Q98078.fctr Q96024.fctr
## 719 Only-child No No
## 1417 Yes No No
## [1] "Category: SKn"
## [1] "max distance(0.9768) pair:"
## USER_ID Party.fctr Hhold.fctr Q124742.fctr Q124122.fctr Q123621.fctr
## 2395 2988 R SKn NA NA NA
## 6279 3607 <NA> SKn NA NA NA
## Q123464.fctr Q122771.fctr Q122770.fctr Q122769.fctr Q122120.fctr
## 2395 NA Pc Yes Yes Yes
## 6279 NA NA NA NA NA
## Q121700.fctr Q121699.fctr Q121011.fctr Q120978.fctr Q120650.fctr
## 2395 Yes Yes Yes No Yes
## 6279 NA NA NA NA NA
## Q120472.fctr Q120379.fctr Q120194.fctr Q120014.fctr Q120012.fctr
## 2395 Art No NA Yes No
## 6279 NA NA NA NA NA
## Q119851.fctr Q119650.fctr Q119334.fctr Q118892.fctr Q118237.fctr
## 2395 Yes Giving NA Yes NA
## 6279 NA NA No Yes No
## Q118233.fctr Q118232.fctr Q118117.fctr Q117193.fctr Q117186.fctr
## 2395 NA NA NA NA NA
## 6279 No Pr Yes Standard hours Cool headed
## Q116797.fctr Q116881.fctr Q116953.fctr Q116601.fctr Q116441.fctr
## 2395 NA NA NA NA NA
## 6279 NA NA NA NA NA
## Q116448.fctr Q116197.fctr Q115602.fctr Q115777.fctr Q115610.fctr
## 2395 NA NA NA NA NA
## 6279 NA NA NA NA NA
## Q115611.fctr Q115899.fctr Q115390.fctr Q115195.fctr Q114961.fctr
## 2395 NA NA NA NA NA
## 6279 NA NA NA NA Yes
## Q114748.fctr Q114517.fctr Q114386.fctr Q114152.fctr Q113992.fctr
## 2395 NA NA NA NA NA
## 6279 Yes No Mysterious Yes NA
## Q113583.fctr Q113584.fctr Q113181.fctr Q112478.fctr Q112512.fctr
## 2395 NA NA NA NA NA
## 6279 Talk Technology NA NA NA
## Q112270.fctr Q111848.fctr Q111580.fctr Q111220.fctr Q110740.fctr
## 2395 NA NA NA NA NA
## 6279 NA Yes NA No NA
## Q109367.fctr Q109244.fctr Q108950.fctr Q108855.fctr Q108617.fctr
## 2395 NA No NA NA NA
## 6279 Yes No Cautious Yes! No
## Q108856.fctr Q108754.fctr Q108342.fctr Q108343.fctr Q107869.fctr
## 2395 NA NA NA NA NA
## 6279 Space No In-person No NA
## Q107491.fctr Q106993.fctr Q106997.fctr Q106272.fctr Q106388.fctr
## 2395 Yes NA NA NA NA
## 6279 NA NA NA NA NA
## Q106389.fctr Q106042.fctr Q105840.fctr Q105655.fctr Q104996.fctr
## 2395 NA NA NA NA No
## 6279 NA NA NA NA NA
## Q103293.fctr Q102906.fctr Q102674.fctr Q102687.fctr Q102289.fctr
## 2395 NA NA NA NA NA
## 6279 NA NA No Yes No
## Q102089.fctr Q101162.fctr Q101163.fctr Q101596.fctr Q100689.fctr
## 2395 NA NA NA NA NA
## 6279 Own Optimist Dad No Yes
## Q100680.fctr Q100562.fctr Q100010.fctr Q99982.fctr Q99716.fctr
## 2395 NA NA NA NA NA
## 6279 No Yes Yes Check! Yes
## Q99581.fctr Q99480.fctr Q98869.fctr Q98578.fctr Q98197.fctr
## 2395 Yes Yes Yes Yes NA
## 6279 NA NA NA NA NA
## Q98059.fctr Q98078.fctr Q96024.fctr
## 2395 Yes Yes Yes
## 6279 NA NA NA
## [1] "min distance(0.9542) pair:"
## USER_ID Party.fctr Hhold.fctr Q124742.fctr Q124122.fctr Q123621.fctr
## 2674 3327 R SKn NA NA NA
## 4650 5804 R SKn NA Yes NA
## Q123464.fctr Q122771.fctr Q122770.fctr Q122769.fctr Q122120.fctr
## 2674 NA NA NA NA NA
## 4650 NA Pc NA NA Yes
## Q121700.fctr Q121699.fctr Q121011.fctr Q120978.fctr Q120650.fctr
## 2674 NA NA NA NA NA
## 4650 Yes No NA NA No
## Q120472.fctr Q120379.fctr Q120194.fctr Q120014.fctr Q120012.fctr
## 2674 NA NA NA NA NA
## 4650 NA NA NA NA NA
## Q119851.fctr Q119650.fctr Q119334.fctr Q118892.fctr Q118237.fctr
## 2674 NA NA NA NA NA
## 4650 NA Giving Yes Yes Yes
## Q118233.fctr Q118232.fctr Q118117.fctr Q117193.fctr Q117186.fctr
## 2674 NA NA NA NA NA
## 4650 No NA Yes Standard hours NA
## Q116797.fctr Q116881.fctr Q116953.fctr Q116601.fctr Q116441.fctr
## 2674 NA NA NA NA No
## 4650 No Happy Yes NA NA
## Q116448.fctr Q116197.fctr Q115602.fctr Q115777.fctr Q115610.fctr
## 2674 No P.M. Yes Start Yes
## 4650 Yes NA Yes Start No
## Q115611.fctr Q115899.fctr Q115390.fctr Q115195.fctr Q114961.fctr
## 2674 Yes Me No Yes Yes
## 4650 Yes Cs No Yes NA
## Q114748.fctr Q114517.fctr Q114386.fctr Q114152.fctr Q113992.fctr
## 2674 No No NA No Yes
## 4650 No No Mysterious NA No
## Q113583.fctr Q113584.fctr Q113181.fctr Q112478.fctr Q112512.fctr
## 2674 Tunes Technology Yes No No
## 4650 Tunes People Yes No Yes
## Q112270.fctr Q111848.fctr Q111580.fctr Q111220.fctr Q110740.fctr
## 2674 Yes No NA NA PC
## 4650 No No Supportive No Mac
## Q109367.fctr Q109244.fctr Q108950.fctr Q108855.fctr Q108617.fctr
## 2674 No No Risk-friendly Umm... No
## 4650 No No Cautious Yes! No
## Q108856.fctr Q108754.fctr Q108342.fctr Q108343.fctr Q107869.fctr
## 2674 Socialize No In-person Yes No
## 4650 Space NA NA NA NA
## Q107491.fctr Q106993.fctr Q106997.fctr Q106272.fctr Q106388.fctr
## 2674 Yes Yes Yy No Yes
## 4650 NA NA NA NA No
## Q106389.fctr Q106042.fctr Q105840.fctr Q105655.fctr Q104996.fctr
## 2674 No No No NA NA
## 4650 No NA Yes No NA
## Q103293.fctr Q102906.fctr Q102674.fctr Q102687.fctr Q102289.fctr
## 2674 NA NA NA NA NA
## 4650 NA NA NA NA NA
## Q102089.fctr Q101162.fctr Q101163.fctr Q101596.fctr Q100689.fctr
## 2674 NA NA NA NA NA
## 4650 NA Pessimist NA NA NA
## Q100680.fctr Q100562.fctr Q100010.fctr Q99982.fctr Q99716.fctr
## 2674 NA NA NA NA No
## 4650 Yes Yes NA NA NA
## Q99581.fctr Q99480.fctr Q98869.fctr Q98578.fctr Q98197.fctr
## 2674 No Yes Yes No Yes
## 4650 NA NA NA Yes Yes
## Q98059.fctr Q98078.fctr Q96024.fctr
## 2674 Yes NA Yes
## 4650 Yes NA No
## [1] "Category: SKy"
## [1] "max distance(0.9760) pair:"
## USER_ID Party.fctr Hhold.fctr Q124742.fctr Q124122.fctr Q123621.fctr
## 2360 2939 D SKy NA NA NA
## 3852 4799 R SKy NA NA NA
## Q123464.fctr Q122771.fctr Q122770.fctr Q122769.fctr Q122120.fctr
## 2360 NA Pc Yes No No
## 3852 NA NA NA NA NA
## Q121700.fctr Q121699.fctr Q121011.fctr Q120978.fctr Q120650.fctr
## 2360 No Yes NA NA Yes
## 3852 NA NA NA NA NA
## Q120472.fctr Q120379.fctr Q120194.fctr Q120014.fctr Q120012.fctr
## 2360 Science Yes Try first No No
## 3852 NA NA NA NA NA
## Q119851.fctr Q119650.fctr Q119334.fctr Q118892.fctr Q118237.fctr
## 2360 Yes Giving NA No Yes
## 3852 NA NA Yes No No
## Q118233.fctr Q118232.fctr Q118117.fctr Q117193.fctr Q117186.fctr
## 2360 Yes NA NA Standard hours Cool headed
## 3852 Yes NA No Odd hours Cool headed
## Q116797.fctr Q116881.fctr Q116953.fctr Q116601.fctr Q116441.fctr
## 2360 No Happy Yes Yes Yes
## 3852 No Happy No Yes Yes
## Q116448.fctr Q116197.fctr Q115602.fctr Q115777.fctr Q115610.fctr
## 2360 No NA NA NA NA
## 3852 No NA NA Start NA
## Q115611.fctr Q115899.fctr Q115390.fctr Q115195.fctr Q114961.fctr
## 2360 NA NA NA NA NA
## 3852 NA Me NA NA NA
## Q114748.fctr Q114517.fctr Q114386.fctr Q114152.fctr Q113992.fctr
## 2360 NA NA NA NA NA
## 3852 Yes No Mysterious No Yes
## Q113583.fctr Q113584.fctr Q113181.fctr Q112478.fctr Q112512.fctr
## 2360 NA NA NA NA NA
## 3852 Tunes Technology NA No Yes
## Q112270.fctr Q111848.fctr Q111580.fctr Q111220.fctr Q110740.fctr
## 2360 NA NA NA NA NA
## 3852 Yes No Supportive No PC
## Q109367.fctr Q109244.fctr Q108950.fctr Q108855.fctr Q108617.fctr
## 2360 Yes No Risk-friendly Yes! NA
## 3852 Yes No NA NA NA
## Q108856.fctr Q108754.fctr Q108342.fctr Q108343.fctr Q107869.fctr
## 2360 Socialize Yes Online Yes No
## 3852 NA NA In-person No Yes
## Q107491.fctr Q106993.fctr Q106997.fctr Q106272.fctr Q106388.fctr
## 2360 Yes No Yy NA NA
## 3852 Yes Yes Gr Yes Yes
## Q106389.fctr Q106042.fctr Q105840.fctr Q105655.fctr Q104996.fctr
## 2360 NA NA NA NA NA
## 3852 Yes NA NA NA NA
## Q103293.fctr Q102906.fctr Q102674.fctr Q102687.fctr Q102289.fctr
## 2360 NA NA NA NA NA
## 3852 NA NA NA NA Yes
## Q102089.fctr Q101162.fctr Q101163.fctr Q101596.fctr Q100689.fctr
## 2360 NA NA NA NA NA
## 3852 Own NA NA NA Yes
## Q100680.fctr Q100562.fctr Q100010.fctr Q99982.fctr Q99716.fctr
## 2360 NA NA NA NA NA
## 3852 No No Yes Check! Yes
## Q99581.fctr Q99480.fctr Q98869.fctr Q98578.fctr Q98197.fctr
## 2360 NA NA NA NA No
## 3852 No Yes Yes No NA
## Q98059.fctr Q98078.fctr Q96024.fctr
## 2360 Yes Yes NA
## 3852 NA NA NA
## [1] "min distance(0.9566) pair:"
## USER_ID Party.fctr Hhold.fctr Q124742.fctr Q124122.fctr Q123621.fctr
## 1423 1771 D SKy NA NA NA
## 3974 4952 R SKy NA NA NA
## Q123464.fctr Q122771.fctr Q122770.fctr Q122769.fctr Q122120.fctr
## 1423 NA NA NA NA NA
## 3974 NA NA NA NA NA
## Q121700.fctr Q121699.fctr Q121011.fctr Q120978.fctr Q120650.fctr
## 1423 NA NA NA NA NA
## 3974 NA NA NA NA NA
## Q120472.fctr Q120379.fctr Q120194.fctr Q120014.fctr Q120012.fctr
## 1423 NA NA NA NA NA
## 3974 NA NA NA NA NA
## Q119851.fctr Q119650.fctr Q119334.fctr Q118892.fctr Q118237.fctr
## 1423 NA NA NA NA NA
## 3974 NA NA NA NA NA
## Q118233.fctr Q118232.fctr Q118117.fctr Q117193.fctr Q117186.fctr
## 1423 NA NA NA NA NA
## 3974 NA NA NA NA NA
## Q116797.fctr Q116881.fctr Q116953.fctr Q116601.fctr Q116441.fctr
## 1423 NA NA NA NA NA
## 3974 NA NA NA NA NA
## Q116448.fctr Q116197.fctr Q115602.fctr Q115777.fctr Q115610.fctr
## 1423 NA NA Yes Start Yes
## 3974 NA NA NA NA NA
## Q115611.fctr Q115899.fctr Q115390.fctr Q115195.fctr Q114961.fctr
## 1423 No Cs Yes Yes No
## 3974 NA NA NA NA NA
## Q114748.fctr Q114517.fctr Q114386.fctr Q114152.fctr Q113992.fctr
## 1423 Yes No TMI NA Yes
## 3974 NA NA NA NA NA
## Q113583.fctr Q113584.fctr Q113181.fctr Q112478.fctr Q112512.fctr
## 1423 NA NA Yes Yes NA
## 3974 Tunes People Yes Yes Yes
## Q112270.fctr Q111848.fctr Q111580.fctr Q111220.fctr Q110740.fctr
## 1423 No Yes Supportive NA NA
## 3974 No Yes Supportive Yes PC
## Q109367.fctr Q109244.fctr Q108950.fctr Q108855.fctr Q108617.fctr
## 1423 Yes No NA NA NA
## 3974 Yes No Cautious NA NA
## Q108856.fctr Q108754.fctr Q108342.fctr Q108343.fctr Q107869.fctr
## 1423 NA NA NA NA NA
## 3974 NA NA NA NA NA
## Q107491.fctr Q106993.fctr Q106997.fctr Q106272.fctr Q106388.fctr
## 1423 NA NA NA NA NA
## 3974 NA NA NA NA NA
## Q106389.fctr Q106042.fctr Q105840.fctr Q105655.fctr Q104996.fctr
## 1423 NA NA NA NA NA
## 3974 NA NA NA NA NA
## Q103293.fctr Q102906.fctr Q102674.fctr Q102687.fctr Q102289.fctr
## 1423 NA NA NA NA NA
## 3974 NA NA NA NA NA
## Q102089.fctr Q101162.fctr Q101163.fctr Q101596.fctr Q100689.fctr
## 1423 NA NA NA NA NA
## 3974 NA NA NA NA NA
## Q100680.fctr Q100562.fctr Q100010.fctr Q99982.fctr Q99716.fctr
## 1423 NA NA NA NA NA
## 3974 NA NA NA NA NA
## Q99581.fctr Q99480.fctr Q98869.fctr Q98578.fctr Q98197.fctr
## 1423 NA NA NA NA NA
## 3974 NA NA NA NA NA
## Q98059.fctr Q98078.fctr Q96024.fctr
## 1423 NA NA NA
## 3974 NA NA NA
## Hhold.fctr .clusterid Hhold.fctr.clusterid D R .entropy .knt
## 1 N 1 N_1 22 29 0.6836979 51
## 2 N 2 N_2 17 23 0.6818546 40
## 3 N 3 N_3 13 15 0.6905940 28
## 4 N 4 N_4 7 18 0.5929533 25
## 5 MKn 1 MKn_1 52 47 0.6918713 99
## 6 MKn 2 MKn_2 25 58 0.6118817 83
## 7 MKn 3 MKn_3 25 39 0.6690268 64
## 8 MKn 4 MKn_4 21 34 0.6649472 55
## 9 MKy 1 MKy_1 97 178 0.6491186 275
## 10 MKy 2 MKy_2 97 107 0.6919452 204
## 11 MKy 3 MKy_3 56 126 0.6172418 182
## 12 MKy 4 MKy_4 56 119 0.6268695 175
## 13 PKn 1 PKn_1 24 15 0.6662784 39
## 14 PKn 2 PKn_2 13 5 0.5908422 18
## 15 PKn 3 PKn_3 3 3 0.6931472 6
## 16 PKy 1 PKy_1 10 3 0.5402041 13
## 17 PKy 2 PKy_2 2 0 0.0000000 2
## 18 PKy 3 PKy_3 1 2 0.6365142 3
## 19 PKy 4 PKy_4 0 2 0.0000000 2
## 20 SKn 1 SKn_1 250 225 0.6917615 475
## 21 SKn 2 SKn_2 116 227 0.6398292 343
## 22 SKn 3 SKn_3 88 105 0.6892628 193
## 23 SKy 1 SKy_1 16 20 0.6869616 36
## 24 SKy 2 SKy_2 17 14 0.6884572 31
## 25 SKy 3 SKy_3 10 7 0.6774944 17
## [1] "glbObsAll$Hhold.fctr$.clusterid Entropy: 0.6609 (98.0048 pct)"## label step_major step_minor label_minor bgn end
## 11 cluster.data 4 0 0 12.802 61.839
## 12 partition.data.training 5 0 0 61.840 NA
## elapsed
## 11 49.037
## 12 NAStep 5.0: partition data training
## [1] "partition.data.training chunk: setup: elapsed: 0.00 secs"## Loading required package: sqldf## Loading required package: gsubfn## Loading required package: proto## Loading required package: RSQLite## Loading required package: DBI## Loading required package: tcltk## Loading required package: reshape2## [1] "partition.data.training chunk: strata_mtrx complete: elapsed: 6.26 secs"
## [1] "partition.data.training chunk: obs_freq_df complete: elapsed: 6.26 secs"
## [1] "lclgetMatrixSimilarity: duration: 16.423000 secs"## Loading required package: sampling##
## Attaching package: 'sampling'## The following object is masked from 'package:caret':
##
## cluster## [1] "lclgetMatrixSimilarity: duration: 10.897000 secs"
## [1] "lclgetMatrixSimilarity: duration: 3.835000 secs"
## [1] "lclgetMatrixSimilarity: duration: 9.292000 secs"
## [1] "Similarity of partitions:"
## cor cosineSmy obs.x obs.y
## 1 0.9999879 0.9254892 OOB Fit
## 2 0.9999877 0.9182758 OOB New
## 3 0.9999877 0.9160134 Fit New## [1] "partition.data.training chunk: Fit/OOB partition complete: elapsed: 48.06 secs"## Party.Democrat Party.Republican Party.NA
## NA NA 622
## Fit 824 1133 NA
## OOB 214 288 NA
## Party.Democrat Party.Republican Party.NA
## NA NA 1
## Fit 0.4210526 0.5789474 NA
## OOB 0.4262948 0.5737052 NA
## Hhold.fctr .n.Fit .n.OOB .n.Tst .freqRatio.Fit .freqRatio.OOB
## 6 SKn 810 201 252 0.413898825 0.40039841
## 2 MKy 680 156 195 0.347470618 0.31075697
## 1 MKn 226 75 94 0.115482882 0.14940239
## 3 N 116 28 33 0.059274400 0.05577689
## 7 SKy 61 23 27 0.031170158 0.04581673
## 4 PKn 50 13 15 0.025549310 0.02589641
## 5 PKy 14 6 6 0.007153807 0.01195219
## .freqRatio.Tst
## 6 0.405144695
## 2 0.313504823
## 1 0.151125402
## 3 0.053054662
## 7 0.043408360
## 4 0.024115756
## 5 0.009646302## [1] "glbObsAll: "## [1] 3081 222## [1] "glbObsTrn: "## [1] 2459 222## [1] "glbObsFit: "## [1] 1957 221## [1] "glbObsOOB: "## [1] 502 221## [1] "glbObsNew: "## [1] 622 221## [1] "partition.data.training chunk: teardown: elapsed: 48.67 secs"## label step_major step_minor label_minor bgn
## 12 partition.data.training 5 0 0 61.840
## 13 select.features 6 0 0 110.583
## end elapsed
## 12 110.582 48.743
## 13 NA NAStep 6.0: select features
```{r select.features, cache=FALSE, echo=FALSE, eval=myevlChunk(glbChunks, glbOut$pfx)}
## Warning in cor(data.matrix(entity_df[, sel_feats]), y =
## as.numeric(entity_df[, : the standard deviation is zero## cor.y exclude.as.feat cor.y.abs cor.high.X
## Q115611.fctr 0.1061227024 0 0.1061227024 NA
## Q113181.fctr 0.0984260825 0 0.0984260825 NA
## .clusterid 0.0937606364 1 0.0937606364 NA
## .clusterid.fctr 0.0937606364 0 0.0937606364 NA
## Q98197.fctr 0.0740068938 0 0.0740068938 NA
## Q116881.fctr 0.0562595864 0 0.0562595864 NA
## Q108855.fctr 0.0552557062 0 0.0552557062 NA
## Q106272.fctr 0.0508423733 0 0.0508423733 NA
## Q122771.fctr 0.0506936997 0 0.0506936997 NA
## Q123621.fctr 0.0496371444 0 0.0496371444 NA
## Q106388.fctr 0.0494091927 0 0.0494091927 NA
## Q110740.fctr 0.0475251274 0 0.0475251274 NA
## USER_ID 0.0451253514 1 0.0451253514 NA
## .pos 0.0449751220 1 0.0449751220 NA
## Q122769.fctr 0.0357238967 0 0.0357238967 NA
## Q120472.fctr 0.0353553175 0 0.0353553175 NA
## Q101596.fctr 0.0310707949 0 0.0310707949 NA
## Q119334.fctr 0.0307545744 0 0.0307545744 NA
## Q114152.fctr 0.0298031360 0 0.0298031360 NA
## Q98869.fctr 0.0279837842 0 0.0279837842 NA
## Q115899.fctr 0.0275355442 0 0.0275355442 NA
## Q116797.fctr 0.0264023055 0 0.0264023055 NA
## YOB.Age.dff 0.0263896332 0 0.0263896332 NA
## Q118232.fctr 0.0263557469 0 0.0263557469 NA
## Gender.fctr 0.0260785749 0 0.0260785749 NA
## Q105655.fctr 0.0254502518 0 0.0254502518 NA
## Q99480.fctr 0.0241968063 0 0.0241968063 NA
## Q123464.fctr 0.0232487747 0 0.0232487747 NA
## Q120650.fctr 0.0228127973 0 0.0228127973 NA
## Q122120.fctr 0.0226963845 0 0.0226963845 NA
## Q107869.fctr 0.0218682393 0 0.0218682393 NA
## Q120014.fctr 0.0202731591 0 0.0202731591 NA
## Q102289.fctr 0.0192468615 0 0.0192468615 NA
## Income.fctr 0.0179840418 0 0.0179840418 NA
## Q122770.fctr 0.0174735493 0 0.0174735493 NA
## Q111580.fctr 0.0170269417 0 0.0170269417 NA
## Q116601.fctr 0.0159184435 0 0.0159184435 NA
## Q117186.fctr 0.0158641235 0 0.0158641235 NA
## Q106993.fctr 0.0151551332 0 0.0151551332 NA
## Q112270.fctr 0.0147892685 0 0.0147892685 NA
## Q101162.fctr 0.0139326027 0 0.0139326027 NA
## Q108856.fctr 0.0128750759 0 0.0128750759 NA
## Q117193.fctr 0.0114974111 0 0.0114974111 NA
## Q116441.fctr 0.0093463969 0 0.0093463969 NA
## Q119851.fctr 0.0089549525 0 0.0089549525 NA
## Q111848.fctr 0.0085442819 0 0.0085442819 NA
## Q98578.fctr 0.0067135887 0 0.0067135887 NA
## Q118892.fctr 0.0063006467 0 0.0063006467 NA
## Q114386.fctr 0.0057240993 0 0.0057240993 NA
## Q120978.fctr 0.0055115231 0 0.0055115231 NA
## Q112512.fctr 0.0053167658 0 0.0053167658 NA
## Q102674.fctr 0.0050627208 0 0.0050627208 NA
## Q96024.fctr 0.0040534729 0 0.0040534729 NA
## Q108950.fctr 0.0039412433 0 0.0039412433 NA
## Q115610.fctr 0.0037395055 0 0.0037395055 NA
## YOB.Age.fctr 0.0031160191 0 0.0031160191 NA
## Q112478.fctr 0.0028932765 0 0.0028932765 NA
## Q116197.fctr 0.0026906806 0 0.0026906806 NA
## Q124742.fctr 0.0025316261 0 0.0025316261 NA
## Q106389.fctr 0.0020182255 0 0.0020182255 NA
## Edn.fctr 0.0013569584 0 0.0013569584 NA
## Q118117.fctr 0.0006385446 0 0.0006385446 NA
## Q100562.fctr 0.0001743827 0 0.0001743827 NA
## Q107491.fctr -0.0001103153 0 0.0001103153 NA
## Q116448.fctr -0.0023584430 0 0.0023584430 NA
## Q108754.fctr -0.0027742157 0 0.0027742157 NA
## Q116953.fctr -0.0029373549 0 0.0029373549 NA
## Q115602.fctr -0.0031238519 0 0.0031238519 NA
## Q118233.fctr -0.0033273008 0 0.0033273008 NA
## Q120012.fctr -0.0039513241 0 0.0039513241 NA
## Q118237.fctr -0.0043335513 0 0.0043335513 NA
## Q99581.fctr -0.0046486977 0 0.0046486977 NA
## .rnorm -0.0048723001 0 0.0048723001 NA
## Q120194.fctr -0.0057263432 0 0.0057263432 NA
## Q115777.fctr -0.0059804934 0 0.0059804934 NA
## Q106997.fctr -0.0063914109 0 0.0063914109 NA
## Q100680.fctr -0.0072431931 0 0.0072431931 NA
## Q113584.fctr -0.0076436688 0 0.0076436688 NA
## Q108343.fctr -0.0079333386 0 0.0079333386 NA
## Q121700.fctr -0.0087942115 0 0.0087942115 NA
## Q105840.fctr -0.0088034036 0 0.0088034036 NA
## Q120379.fctr -0.0089842116 0 0.0089842116 NA
## Q103293.fctr -0.0090167793 0 0.0090167793 NA
## Q124122.fctr -0.0099503887 0 0.0099503887 NA
## Q109367.fctr -0.0100116070 0 0.0100116070 NA
## Q113992.fctr -0.0100378101 0 0.0100378101 NA
## Q121699.fctr -0.0121369662 0 0.0121369662 NA
## Q121011.fctr -0.0122186222 0 0.0122186222 NA
## Q114748.fctr -0.0128363203 0 0.0128363203 NA
## Q106042.fctr -0.0135167901 0 0.0135167901 NA
## Q111220.fctr -0.0145971279 0 0.0145971279 NA
## Q114517.fctr -0.0148538356 0 0.0148538356 NA
## YOB -0.0169432580 1 0.0169432580 NA
## Q102687.fctr -0.0169904229 0 0.0169904229 NA
## Q102906.fctr -0.0173704239 0 0.0173704239 NA
## Q98078.fctr -0.0177772661 0 0.0177772661 NA
## Q115390.fctr -0.0196547694 0 0.0196547694 NA
## Q102089.fctr -0.0200451075 0 0.0200451075 NA
## Q100010.fctr -0.0208031518 0 0.0208031518 NA
## Q99982.fctr -0.0208604939 0 0.0208604939 NA
## Q113583.fctr -0.0211296876 0 0.0211296876 NA
## Q108342.fctr -0.0211946324 0 0.0211946324 NA
## Q104996.fctr -0.0218776356 0 0.0218776356 NA
## Q119650.fctr -0.0222628005 0 0.0222628005 NA
## Q100689.fctr -0.0263249102 0 0.0263249102 NA
## Q108617.fctr -0.0285334447 0 0.0285334447 NA
## Q115195.fctr -0.0295831061 0 0.0295831061 NA
## Q99716.fctr -0.0333178411 0 0.0333178411 NA
## Q101163.fctr -0.0349739760 0 0.0349739760 NA
## Q98059.fctr -0.0354482758 0 0.0354482758 NA
## Q114961.fctr -0.0396043459 0 0.0396043459 NA
## Hhold.fctr -0.0644984804 0 0.0644984804 NA
## Q109244.fctr NA 0 NA NA
## freqRatio percentUnique zeroVar nzv is.cor.y.abs.low
## Q115611.fctr 1.346501 0.12200081 FALSE FALSE FALSE
## Q113181.fctr 1.207806 0.12200081 FALSE FALSE FALSE
## .clusterid 1.370319 0.16266775 FALSE FALSE FALSE
## .clusterid.fctr 1.370319 0.16266775 FALSE FALSE FALSE
## Q98197.fctr 1.293258 0.12200081 FALSE FALSE FALSE
## Q116881.fctr 2.244592 0.12200081 FALSE FALSE FALSE
## Q108855.fctr 1.511876 0.12200081 FALSE FALSE FALSE
## Q106272.fctr 2.712785 0.12200081 FALSE FALSE FALSE
## Q122771.fctr 3.656388 0.12200081 FALSE FALSE FALSE
## Q123621.fctr 1.144186 0.12200081 FALSE FALSE FALSE
## Q106388.fctr 2.478261 0.12200081 FALSE FALSE FALSE
## Q110740.fctr 1.491409 0.12200081 FALSE FALSE FALSE
## USER_ID 1.000000 100.00000000 FALSE FALSE FALSE
## .pos 1.000000 100.00000000 FALSE FALSE FALSE
## Q122769.fctr 1.693260 0.12200081 FALSE FALSE FALSE
## Q120472.fctr 2.803119 0.12200081 FALSE FALSE FALSE
## Q101596.fctr 1.737877 0.12200081 FALSE FALSE FALSE
## Q119334.fctr 1.125395 0.12200081 FALSE FALSE FALSE
## Q114152.fctr 2.270531 0.12200081 FALSE FALSE FALSE
## Q98869.fctr 3.614191 0.12200081 FALSE FALSE FALSE
## Q115899.fctr 1.448234 0.12200081 FALSE FALSE FALSE
## Q116797.fctr 2.093023 0.12200081 FALSE FALSE FALSE
## YOB.Age.dff 1.021687 0.73200488 FALSE FALSE FALSE
## Q118232.fctr 1.307600 0.12200081 FALSE FALSE FALSE
## Gender.fctr 2.405063 0.12200081 FALSE FALSE FALSE
## Q105655.fctr 1.274947 0.12200081 FALSE FALSE FALSE
## Q99480.fctr 4.095588 0.12200081 FALSE FALSE FALSE
## Q123464.fctr 3.190731 0.12200081 FALSE FALSE FALSE
## Q120650.fctr 3.544379 0.12200081 FALSE FALSE FALSE
## Q122120.fctr 3.098563 0.12200081 FALSE FALSE FALSE
## Q107869.fctr 1.293617 0.12200081 FALSE FALSE FALSE
## Q120014.fctr 1.623324 0.12200081 FALSE FALSE FALSE
## Q102289.fctr 2.286846 0.12200081 FALSE FALSE FALSE
## Income.fctr 1.026596 0.28466856 FALSE FALSE FALSE
## Q122770.fctr 1.407720 0.12200081 FALSE FALSE FALSE
## Q111580.fctr 1.934936 0.12200081 FALSE FALSE FALSE
## Q116601.fctr 3.948235 0.12200081 FALSE FALSE FALSE
## Q117186.fctr 1.761702 0.12200081 FALSE FALSE FALSE
## Q106993.fctr 4.903581 0.12200081 FALSE FALSE FALSE
## Q112270.fctr 1.134313 0.12200081 FALSE FALSE FALSE
## Q101162.fctr 1.556382 0.12200081 FALSE FALSE FALSE
## Q108856.fctr 2.251156 0.12200081 FALSE FALSE FALSE
## Q117193.fctr 1.346618 0.12200081 FALSE FALSE FALSE
## Q116441.fctr 1.638601 0.12200081 FALSE FALSE FALSE
## Q119851.fctr 1.575758 0.12200081 FALSE FALSE FALSE
## Q111848.fctr 1.402247 0.12200081 FALSE FALSE FALSE
## Q98578.fctr 1.717158 0.12200081 FALSE FALSE FALSE
## Q118892.fctr 1.411356 0.12200081 FALSE FALSE FALSE
## Q114386.fctr 1.426366 0.12200081 FALSE FALSE FALSE
## Q120978.fctr 1.264000 0.12200081 FALSE FALSE FALSE
## Q112512.fctr 4.175743 0.12200081 FALSE FALSE FALSE
## Q102674.fctr 1.849030 0.12200081 FALSE FALSE FALSE
## Q96024.fctr 1.683444 0.12200081 FALSE FALSE TRUE
## Q108950.fctr 2.087366 0.12200081 FALSE FALSE TRUE
## Q115610.fctr 3.966825 0.12200081 FALSE FALSE TRUE
## YOB.Age.fctr 1.180000 0.36600244 FALSE FALSE TRUE
## Q112478.fctr 1.459880 0.12200081 FALSE FALSE TRUE
## Q116197.fctr 2.031484 0.12200081 FALSE FALSE TRUE
## Q124742.fctr 1.322468 0.12200081 FALSE FALSE TRUE
## Q106389.fctr 1.086957 0.12200081 FALSE FALSE TRUE
## Edn.fctr 1.694524 0.32533550 FALSE FALSE TRUE
## Q118117.fctr 1.402074 0.12200081 FALSE FALSE TRUE
## Q100562.fctr 4.329082 0.12200081 FALSE FALSE TRUE
## Q107491.fctr 6.288591 0.12200081 FALSE FALSE TRUE
## Q116448.fctr 1.352326 0.12200081 FALSE FALSE TRUE
## Q108754.fctr 2.045897 0.12200081 FALSE FALSE TRUE
## Q116953.fctr 1.978788 0.12200081 FALSE FALSE TRUE
## Q115602.fctr 3.864608 0.12200081 FALSE FALSE TRUE
## Q118233.fctr 2.654676 0.12200081 FALSE FALSE TRUE
## Q120012.fctr 1.344262 0.12200081 FALSE FALSE TRUE
## Q118237.fctr 1.429419 0.12200081 FALSE FALSE TRUE
## Q99581.fctr 4.989011 0.12200081 FALSE FALSE TRUE
## .rnorm 1.000000 100.00000000 FALSE FALSE FALSE
## Q120194.fctr 1.317536 0.12200081 FALSE FALSE FALSE
## Q115777.fctr 1.387173 0.12200081 FALSE FALSE FALSE
## Q106997.fctr 1.187117 0.12200081 FALSE FALSE FALSE
## Q100680.fctr 1.250542 0.12200081 FALSE FALSE FALSE
## Q113584.fctr 1.008824 0.12200081 FALSE FALSE FALSE
## Q108343.fctr 1.565774 0.12200081 FALSE FALSE FALSE
## Q121700.fctr 3.968468 0.12200081 FALSE FALSE FALSE
## Q105840.fctr 1.486260 0.12200081 FALSE FALSE FALSE
## Q120379.fctr 1.447596 0.12200081 FALSE FALSE FALSE
## Q103293.fctr 1.252910 0.12200081 FALSE FALSE FALSE
## Q124122.fctr 1.187500 0.12200081 FALSE FALSE FALSE
## Q109367.fctr 1.460805 0.12200081 FALSE FALSE FALSE
## Q113992.fctr 2.253086 0.12200081 FALSE FALSE FALSE
## Q121699.fctr 2.600355 0.12200081 FALSE FALSE FALSE
## Q121011.fctr 1.158969 0.12200081 FALSE FALSE FALSE
## Q114748.fctr 1.344482 0.12200081 FALSE FALSE FALSE
## Q106042.fctr 1.319690 0.12200081 FALSE FALSE FALSE
## Q111220.fctr 3.014898 0.12200081 FALSE FALSE FALSE
## Q114517.fctr 2.182796 0.12200081 FALSE FALSE FALSE
## YOB 1.105769 2.92801952 FALSE FALSE FALSE
## Q102687.fctr 1.004803 0.12200081 FALSE FALSE FALSE
## Q102906.fctr 1.950213 0.12200081 FALSE FALSE FALSE
## Q98078.fctr 1.590206 0.12200081 FALSE FALSE FALSE
## Q115390.fctr 1.460576 0.12200081 FALSE FALSE FALSE
## Q102089.fctr 2.381260 0.12200081 FALSE FALSE FALSE
## Q100010.fctr 3.962529 0.12200081 FALSE FALSE FALSE
## Q99982.fctr 1.107143 0.12200081 FALSE FALSE FALSE
## Q113583.fctr 1.881690 0.12200081 FALSE FALSE FALSE
## Q108342.fctr 2.426563 0.12200081 FALSE FALSE FALSE
## Q104996.fctr 1.032350 0.12200081 FALSE FALSE FALSE
## Q119650.fctr 3.108830 0.12200081 FALSE FALSE FALSE
## Q100689.fctr 1.440137 0.12200081 FALSE FALSE FALSE
## Q108617.fctr 7.888446 0.12200081 FALSE FALSE FALSE
## Q115195.fctr 1.713147 0.12200081 FALSE FALSE FALSE
## Q99716.fctr 4.852332 0.12200081 FALSE FALSE FALSE
## Q101163.fctr 1.437576 0.12200081 FALSE FALSE FALSE
## Q98059.fctr 5.379888 0.12200081 FALSE FALSE FALSE
## Q114961.fctr 1.029000 0.12200081 FALSE FALSE FALSE
## Hhold.fctr 1.209330 0.28466856 FALSE FALSE FALSE
## Q109244.fctr 0.000000 0.04066694 TRUE TRUE NA## Warning in myplot_scatter(plt_feats_df, "percentUnique", "freqRatio",
## colorcol_name = "nzv", : converting nzv to class:factor## Warning: Removed 3 rows containing missing values (geom_point).
## Warning: Removed 3 rows containing missing values (geom_point).
## Warning: Removed 3 rows containing missing values (geom_point).
## cor.y exclude.as.feat cor.y.abs cor.high.X freqRatio
## Q109244.fctr NA 0 NA NA 0
## percentUnique zeroVar nzv is.cor.y.abs.low
## Q109244.fctr 0.04066694 TRUE TRUE NA## Scale for 'y' is already present. Adding another scale for 'y', which
## will replace the existing scale.
## [1] "numeric data missing in : "
## YOB Party.fctr
## 128 622
## [1] "numeric data w/ 0s in : "
## YOB.Age.dff
## 136
## [1] "numeric data w/ Infs in : "
## named integer(0)
## [1] "numeric data w/ NaNs in : "
## named integer(0)
## [1] "string data missing in : "
## Gender Income HouseholdStatus EducationLevel
## 46 445 177 410
## Party Q124742 Q124122 Q123464
## NA 1438 823 708
## Q123621 Q122769 Q122770 Q122771
## 778 644 594 587
## Q122120 Q121699 Q121700 Q120978
## 585 547 563 599
## Q121011 Q120379 Q120650 Q120472
## 571 607 655 649
## Q120194 Q120012 Q120014 Q119334
## 654 591 641 568
## Q119851 Q119650 Q118892 Q118117
## 540 578 486 479
## Q118232 Q118233 Q118237 Q117186
## 701 554 539 648
## Q117193 Q116797 Q116881 Q116953
## 655 590 635 616
## Q116601 Q116441 Q116448 Q116197
## 534 541 560 551
## Q115602 Q115777 Q115610 Q115611
## 539 578 537 487
## Q115899 Q115390 Q114961 Q114748
## 573 619 538 447
## Q115195 Q114517 Q114386 Q113992
## 525 481 521 447
## Q114152 Q113583 Q113584 Q113181
## 537 514 512 453
## Q112478 Q112512 Q112270 Q111848
## 494 460 521 398
## Q111580 Q111220 Q110740 Q109367
## 474 379 357 168
## Q108950 Q109244 Q108855 Q108617
## 204 0 438 288
## Q108856 Q108754 Q108342 Q108343
## 436 338 341 333
## Q107869 Q107491 Q106993 Q106997
## 389 366 389 396
## Q106272 Q106388 Q106389 Q106042
## 426 476 495 451
## Q105840 Q105655 Q104996 Q103293
## 487 393 400 431
## Q102906 Q102674 Q102687 Q102289
## 493 511 475 484
## Q102089 Q101162 Q101163 Q101596
## 462 498 572 477
## Q100689 Q100680 Q100562 Q99982
## 414 497 487 514
## Q100010 Q99716 Q99581 Q99480
## 445 500 466 478
## Q98869 Q98578 Q98059 Q98078
## 564 542 450 569
## Q98197 Q96024 .lcn
## 528 550 622## [1] "glb_feats_df:"## [1] 113 12## id exclude.as.feat rsp_var
## Party.fctr Party.fctr TRUE TRUE## id cor.y exclude.as.feat cor.y.abs cor.high.X
## USER_ID USER_ID 0.04512535 TRUE 0.04512535 NA
## Party.fctr Party.fctr NA TRUE NA NA
## freqRatio percentUnique zeroVar nzv is.cor.y.abs.low
## USER_ID 1 100 FALSE FALSE FALSE
## Party.fctr NA NA NA NA NA
## interaction.feat shapiro.test.p.value rsp_var_raw id_var
## USER_ID <NA> NA FALSE TRUE
## Party.fctr <NA> NA NA NA
## rsp_var
## USER_ID NA
## Party.fctr TRUE## [1] "glb_feats_df vs. glbObsAll: "## character(0)## [1] "glbObsAll vs. glb_feats_df: "## character(0)## label step_major step_minor label_minor bgn end
## 13 select.features 6 0 0 110.583 113.283
## 14 fit.models 7 0 0 113.283 NA
## elapsed
## 13 2.7
## 14 NAStep 7.0: fit models
fit.models_0_chunk_df <- myadd_chunk(NULL, "fit.models_0_bgn", label.minor = "setup")## label step_major step_minor label_minor bgn end elapsed
## 1 fit.models_0_bgn 1 0 setup 113.809 NA NA# load(paste0(glbOut$pfx, "dsk.RData"))
glbgetModelSelectFormula <- function() {
model_evl_terms <- c(NULL)
# min.aic.fit might not be avl
lclMdlEvlCriteria <-
glbMdlMetricsEval[glbMdlMetricsEval %in% names(glb_models_df)]
for (metric in lclMdlEvlCriteria)
model_evl_terms <- c(model_evl_terms,
ifelse(length(grep("max", metric)) > 0, "-", "+"), metric)
if (glb_is_classification && glb_is_binomial)
model_evl_terms <- c(model_evl_terms, "-", "opt.prob.threshold.OOB")
model_sel_frmla <- as.formula(paste(c("~ ", model_evl_terms), collapse = " "))
return(model_sel_frmla)
}
glbgetDisplayModelsDf <- function() {
dsp_models_cols <- c("id",
glbMdlMetricsEval[glbMdlMetricsEval %in% names(glb_models_df)],
grep("opt.", names(glb_models_df), fixed = TRUE, value = TRUE))
dsp_models_df <-
#orderBy(glbgetModelSelectFormula(), glb_models_df)[, c("id", glbMdlMetricsEval)]
orderBy(glbgetModelSelectFormula(), glb_models_df)[, dsp_models_cols]
nCvMdl <- sapply(glb_models_lst, function(mdl) nrow(mdl$results))
nParams <- sapply(glb_models_lst, function(mdl) ifelse(mdl$method == "custom", 0,
nrow(subset(modelLookup(mdl$method), parameter != "parameter"))))
# nCvMdl <- nCvMdl[names(nCvMdl) != "avNNet"]
# nParams <- nParams[names(nParams) != "avNNet"]
if (length(cvMdlProblems <- nCvMdl[nCvMdl <= nParams]) > 0) {
print("Cross Validation issues:")
warning("Cross Validation issues:")
print(cvMdlProblems)
}
pltMdls <- setdiff(names(nCvMdl), names(cvMdlProblems))
pltMdls <- setdiff(pltMdls, names(nParams[nParams == 0]))
# length(pltMdls) == 21
png(paste0(glbOut$pfx, "bestTune.png"), width = 480 * 2, height = 480 * 4)
grid.newpage()
pushViewport(viewport(layout = grid.layout(ceiling(length(pltMdls) / 2.0), 2)))
pltIx <- 1
for (mdlId in pltMdls) {
print(ggplot(glb_models_lst[[mdlId]], highBestTune = TRUE) + labs(title = mdlId),
vp = viewport(layout.pos.row = ceiling(pltIx / 2.0),
layout.pos.col = ((pltIx - 1) %% 2) + 1))
pltIx <- pltIx + 1
}
dev.off()
if (all(row.names(dsp_models_df) != dsp_models_df$id))
row.names(dsp_models_df) <- dsp_models_df$id
return(dsp_models_df)
}
#glbgetDisplayModelsDf()
glb_get_predictions <- function(df, mdl_id, rsp_var, prob_threshold_def=NULL, verbose=FALSE) {
mdl <- glb_models_lst[[mdl_id]]
clmnNames <- mygetPredictIds(rsp_var, mdl_id)
predct_var_name <- clmnNames$value
predct_prob_var_name <- clmnNames$prob
predct_accurate_var_name <- clmnNames$is.acc
predct_error_var_name <- clmnNames$err
predct_erabs_var_name <- clmnNames$err.abs
if (glb_is_regression) {
df[, predct_var_name] <- predict(mdl, newdata=df, type="raw")
if (verbose) print(myplot_scatter(df, glb_rsp_var, predct_var_name) +
facet_wrap(reformulate(glbFeatsCategory), scales = "free") +
stat_smooth(method="glm"))
df[, predct_error_var_name] <- df[, predct_var_name] - df[, glb_rsp_var]
if (verbose) print(myplot_scatter(df, predct_var_name, predct_error_var_name) +
#facet_wrap(reformulate(glbFeatsCategory), scales = "free") +
stat_smooth(method="auto"))
if (verbose) print(myplot_scatter(df, glb_rsp_var, predct_error_var_name) +
#facet_wrap(reformulate(glbFeatsCategory), scales = "free") +
stat_smooth(method="glm"))
df[, predct_erabs_var_name] <- abs(df[, predct_error_var_name])
if (verbose) print(head(orderBy(reformulate(c("-", predct_erabs_var_name)), df)))
df[, predct_accurate_var_name] <- (df[, glb_rsp_var] == df[, predct_var_name])
}
if (glb_is_classification && glb_is_binomial) {
prob_threshold <- glb_models_df[glb_models_df$id == mdl_id,
"opt.prob.threshold.OOB"]
if (is.null(prob_threshold) || is.na(prob_threshold)) {
warning("Using default probability threshold: ", prob_threshold_def)
if (is.null(prob_threshold <- prob_threshold_def))
stop("Default probability threshold is NULL")
}
df[, predct_prob_var_name] <- predict(mdl, newdata = df, type = "prob")[, 2]
df[, predct_var_name] <-
factor(levels(df[, glb_rsp_var])[
(df[, predct_prob_var_name] >=
prob_threshold) * 1 + 1], levels(df[, glb_rsp_var]))
# if (verbose) print(myplot_scatter(df, glb_rsp_var, predct_var_name) +
# facet_wrap(reformulate(glbFeatsCategory), scales = "free") +
# stat_smooth(method="glm"))
df[, predct_error_var_name] <- df[, predct_var_name] != df[, glb_rsp_var]
# if (verbose) print(myplot_scatter(df, predct_var_name, predct_error_var_name) +
# #facet_wrap(reformulate(glbFeatsCategory), scales = "free") +
# stat_smooth(method="auto"))
# if (verbose) print(myplot_scatter(df, glb_rsp_var, predct_error_var_name) +
# #facet_wrap(reformulate(glbFeatsCategory), scales = "free") +
# stat_smooth(method="glm"))
# if prediction is a TP (true +ve), measure distance from 1.0
tp <- which((df[, predct_var_name] == df[, glb_rsp_var]) &
(df[, predct_var_name] == levels(df[, glb_rsp_var])[2]))
df[tp, predct_erabs_var_name] <- abs(1 - df[tp, predct_prob_var_name])
#rowIx <- which.max(df[tp, predct_erabs_var_name]); df[tp, c(glbFeatsId, glb_rsp_var, predct_var_name, predct_prob_var_name, predct_erabs_var_name)][rowIx, ]
# if prediction is a TN (true -ve), measure distance from 0.0
tn <- which((df[, predct_var_name] == df[, glb_rsp_var]) &
(df[, predct_var_name] == levels(df[, glb_rsp_var])[1]))
df[tn, predct_erabs_var_name] <- abs(0 - df[tn, predct_prob_var_name])
#rowIx <- which.max(df[tn, predct_erabs_var_name]); df[tn, c(glbFeatsId, glb_rsp_var, predct_var_name, predct_prob_var_name, predct_erabs_var_name)][rowIx, ]
# if prediction is a FP (flse +ve), measure distance from 0.0
fp <- which((df[, predct_var_name] != df[, glb_rsp_var]) &
(df[, predct_var_name] == levels(df[, glb_rsp_var])[2]))
df[fp, predct_erabs_var_name] <- abs(0 - df[fp, predct_prob_var_name])
#rowIx <- which.max(df[fp, predct_erabs_var_name]); df[fp, c(glbFeatsId, glb_rsp_var, predct_var_name, predct_prob_var_name, predct_erabs_var_name)][rowIx, ]
# if prediction is a FN (flse -ve), measure distance from 1.0
fn <- which((df[, predct_var_name] != df[, glb_rsp_var]) &
(df[, predct_var_name] == levels(df[, glb_rsp_var])[1]))
df[fn, predct_erabs_var_name] <- abs(1 - df[fn, predct_prob_var_name])
#rowIx <- which.max(df[fn, predct_erabs_var_name]); df[fn, c(glbFeatsId, glb_rsp_var, predct_var_name, predct_prob_var_name, predct_erabs_var_name)][rowIx, ]
if (verbose) print(head(orderBy(reformulate(c("-", predct_erabs_var_name)), df)))
df[, predct_accurate_var_name] <- (df[, glb_rsp_var] == df[, predct_var_name])
}
if (glb_is_classification && !glb_is_binomial) {
df[, predct_var_name] <- predict(mdl, newdata = df, type = "raw")
probCls <- predict(mdl, newdata = df, type = "prob")
df[, predct_prob_var_name] <- NA
for (cls in names(probCls)) {
mask <- (df[, predct_var_name] == cls)
df[mask, predct_prob_var_name] <- probCls[mask, cls]
}
if (verbose) print(myplot_histogram(df, predct_prob_var_name,
fill_col_name = predct_var_name))
if (verbose) print(myplot_histogram(df, predct_prob_var_name,
facet_frmla = paste0("~", glb_rsp_var)))
df[, predct_error_var_name] <- df[, predct_var_name] != df[, glb_rsp_var]
# if prediction is erroneous, measure predicted class prob from actual class prob
df[, predct_erabs_var_name] <- 0
for (cls in names(probCls)) {
mask <- (df[, glb_rsp_var] == cls) & (df[, predct_error_var_name])
df[mask, predct_erabs_var_name] <- probCls[mask, cls]
}
df[, predct_accurate_var_name] <- (df[, glb_rsp_var] == df[, predct_var_name])
}
return(df)
}
if (glb_is_classification && glb_is_binomial &&
(length(unique(glbObsFit[, glb_rsp_var])) < 2))
stop("glbObsFit$", glb_rsp_var, ": contains less than 2 unique values: ",
paste0(unique(glbObsFit[, glb_rsp_var]), collapse=", "))
max_cor_y_x_vars <- orderBy(~ -cor.y.abs,
subset(glb_feats_df, (exclude.as.feat == 0) & !nzv & !is.cor.y.abs.low &
is.na(cor.high.X)))[1:2, "id"]
max_cor_y_x_vars <- max_cor_y_x_vars[!is.na(max_cor_y_x_vars)]
if (length(max_cor_y_x_vars) < 2)
max_cor_y_x_vars <- union(max_cor_y_x_vars, ".pos")
if (!is.null(glb_Baseline_mdl_var)) {
if ((max_cor_y_x_vars[1] != glb_Baseline_mdl_var) &
(glb_feats_df[glb_feats_df$id == max_cor_y_x_vars[1], "cor.y.abs"] >
glb_feats_df[glb_feats_df$id == glb_Baseline_mdl_var, "cor.y.abs"]))
stop(max_cor_y_x_vars[1], " has a higher correlation with ", glb_rsp_var,
" than the Baseline var: ", glb_Baseline_mdl_var)
}
glb_model_type <- ifelse(glb_is_regression, "regression", "classification")
# Model specs
# c("id.prefix", "method", "type",
# # trainControl params
# "preProc.method", "cv.n.folds", "cv.n.repeats", "summary.fn",
# # train params
# "metric", "metric.maximize", "tune.df")
# Baseline
if (!is.null(glb_Baseline_mdl_var)) {
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Baseline"), major.inc = FALSE,
label.minor = "mybaseln_classfr")
ret_lst <- myfit_mdl(mdl_id="Baseline",
model_method="mybaseln_classfr",
indepVar=glb_Baseline_mdl_var,
rsp_var=glb_rsp_var,
fit_df=glbObsFit, OOB_df=glbObsOOB)
}
# Most Frequent Outcome "MFO" model: mean(y) for regression
# Not using caret's nullModel since model stats not avl
# Cannot use rpart for multinomial classification since it predicts non-MFO
if (glb_is_classification) {
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "MFO"), major.inc = FALSE,
label.minor = "myMFO_classfr")
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "MFO", type = glb_model_type, trainControl.method = "none",
train.method = ifelse(glb_is_regression, "lm", "myMFO_classfr"))),
indepVar = ".rnorm", rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
# "random" model - only for classification;
# none needed for regression since it is same as MFO
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Random"), major.inc = FALSE,
label.minor = "myrandom_classfr")
#stop(here"); glb2Sav(); all.equal(glb_models_df, sav_models_df)
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Random", type = glb_model_type, trainControl.method = "none",
train.method = "myrandom_classfr")),
indepVar = ".rnorm", rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
}## label step_major step_minor label_minor bgn end
## 1 fit.models_0_bgn 1 0 setup 113.809 113.845
## 2 fit.models_0_MFO 1 1 myMFO_classfr 113.845 NA
## elapsed
## 1 0.036
## 2 NA
## [1] "myfit_mdl: enter: 0.002000 secs"
## [1] "myfit_mdl: fitting model: MFO###myMFO_classfr"
## [1] " indepVar: .rnorm"
## [1] "myfit_mdl: setup complete: 0.410000 secs"
## Fitting parameter = none on full training set
## [1] "in MFO.Classifier$fit"
## [1] "unique.vals:"
## [1] D R
## Levels: D R
## [1] "unique.prob:"
## y
## R D
## 0.5789474 0.4210526
## [1] "MFO.val:"
## [1] "R"
## [1] "myfit_mdl: train complete: 0.891000 secs"
## parameter
## 1 none
## Length Class Mode
## unique.vals 2 factor numeric
## unique.prob 2 -none- numeric
## MFO.val 1 -none- character
## x.names 1 -none- character
## xNames 1 -none- character
## problemType 1 -none- character
## tuneValue 1 data.frame list
## obsLevels 2 -none- character## Warning in if (mdl_specs_lst[["train.method"]] == "glm")
## mydisplayOutliers(mdl, : the condition has length > 1 and only the first
## element will be used## [1] "myfit_mdl: train diagnostics complete: 0.894000 secs"## Loading required namespace: pROC## [1] "entr MFO.Classifier$predict"
## [1] "exit MFO.Classifier$predict"## Loading required package: ROCR## Loading required package: gplots##
## Attaching package: 'gplots'## The following object is masked from 'package:stats':
##
## lowess## [1] "in MFO.Classifier$prob"
## D R
## 1 0.5789474 0.4210526
## 2 0.5789474 0.4210526
## 3 0.5789474 0.4210526
## 4 0.5789474 0.4210526
## 5 0.5789474 0.4210526
## 6 0.5789474 0.4210526
## Prediction
## Reference D R
## D 0 824
## R 0 1133
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 5.789474e-01 0.000000e+00 5.567125e-01 6.009453e-01 5.789474e-01
## AccuracyPValue McnemarPValue
## 5.096118e-01 8.885492e-181
## [1] "entr MFO.Classifier$predict"
## [1] "exit MFO.Classifier$predict"
## [1] "in MFO.Classifier$prob"
## D R
## 1 0.5789474 0.4210526
## 2 0.5789474 0.4210526
## 3 0.5789474 0.4210526
## 4 0.5789474 0.4210526
## 5 0.5789474 0.4210526
## 6 0.5789474 0.4210526## Prediction
## Reference D R
## D 0 214
## R 0 288
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 5.737052e-01 0.000000e+00 5.291204e-01 6.174170e-01 5.737052e-01
## AccuracyPValue McnemarPValue
## 5.188758e-01 5.017792e-48
## [1] "myfit_mdl: predict complete: 6.695000 secs"
## id feats max.nTuningRuns min.elapsedtime.everything
## 1 MFO###myMFO_classfr .rnorm 0 0.473
## min.elapsedtime.final max.AUCpROC.fit max.Sens.fit max.Spec.fit
## 1 0.003 0.5 0 1
## max.AUCROCR.fit opt.prob.threshold.fit max.f.score.fit max.Accuracy.fit
## 1 0.5 0.4 0.7333333 0.5789474
## max.AccuracyLower.fit max.AccuracyUpper.fit max.Kappa.fit
## 1 0.5567125 0.6009453 0
## max.AUCpROC.OOB max.Sens.OOB max.Spec.OOB max.AUCROCR.OOB
## 1 0.5 0 1 0.5
## opt.prob.threshold.OOB max.f.score.OOB max.Accuracy.OOB
## 1 0.4 0.7291139 0.5737052
## max.AccuracyLower.OOB max.AccuracyUpper.OOB max.Kappa.OOB
## 1 0.5291204 0.617417 0
## [1] "in MFO.Classifier$prob"
## D R
## 1 0.5789474 0.4210526
## 2 0.5789474 0.4210526
## 3 0.5789474 0.4210526
## 4 0.5789474 0.4210526
## 5 0.5789474 0.4210526
## 6 0.5789474 0.4210526
## [1] "myfit_mdl: exit: 6.767000 secs"
## label step_major step_minor label_minor bgn
## 2 fit.models_0_MFO 1 1 myMFO_classfr 113.845
## 3 fit.models_0_Random 1 2 myrandom_classfr 120.619
## end elapsed
## 2 120.618 6.773
## 3 NA NA
## [1] "myfit_mdl: enter: 0.001000 secs"
## [1] "myfit_mdl: fitting model: Random###myrandom_classfr"
## [1] " indepVar: .rnorm"
## [1] "myfit_mdl: setup complete: 0.410000 secs"
## Fitting parameter = none on full training set
## [1] "myfit_mdl: train complete: 0.681000 secs"
## parameter
## 1 none
## Length Class Mode
## unique.vals 2 factor numeric
## unique.prob 2 table numeric
## xNames 1 -none- character
## problemType 1 -none- character
## tuneValue 1 data.frame list
## obsLevels 2 -none- character## Warning in if (mdl_specs_lst[["train.method"]] == "glm")
## mydisplayOutliers(mdl, : the condition has length > 1 and only the first
## element will be used
## [1] "myfit_mdl: train diagnostics complete: 0.683000 secs"
## [1] "in Random.Classifier$prob"
## Prediction
## Reference D R
## D 0 824
## R 0 1133
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 5.789474e-01 0.000000e+00 5.567125e-01 6.009453e-01 5.789474e-01
## AccuracyPValue McnemarPValue
## 5.096118e-01 8.885492e-181
## [1] "in Random.Classifier$prob"
## Prediction
## Reference D R
## D 0 214
## R 0 288
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 5.737052e-01 0.000000e+00 5.291204e-01 6.174170e-01 5.737052e-01
## AccuracyPValue McnemarPValue
## 5.188758e-01 5.017792e-48
## [1] "myfit_mdl: predict complete: 6.812000 secs"
## id feats max.nTuningRuns
## 1 Random###myrandom_classfr .rnorm 0
## min.elapsedtime.everything min.elapsedtime.final max.AUCpROC.fit
## 1 0.266 0.002 0.4992277
## max.Sens.fit max.Spec.fit max.AUCROCR.fit opt.prob.threshold.fit
## 1 0.4150485 0.5834069 0.5146734 0.4
## max.f.score.fit max.Accuracy.fit max.AccuracyLower.fit
## 1 0.7333333 0.5789474 0.5567125
## max.AccuracyUpper.fit max.Kappa.fit max.AUCpROC.OOB max.Sens.OOB
## 1 0.6009453 0 0.4990752 0.4252336
## max.Spec.OOB max.AUCROCR.OOB opt.prob.threshold.OOB max.f.score.OOB
## 1 0.5729167 0.5181075 0.4 0.7291139
## max.Accuracy.OOB max.AccuracyLower.OOB max.AccuracyUpper.OOB
## 1 0.5737052 0.5291204 0.617417
## max.Kappa.OOB
## 1 0
## [1] "in Random.Classifier$prob"
## [1] "myfit_mdl: exit: 7.614000 secs"# Max.cor.Y
# Check impact of cv
# rpart is not a good candidate since caret does not optimize cp (only tuning parameter of rpart) well
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Max.cor.Y.rcv.*X*"), major.inc = FALSE,
label.minor = "glmnet")## label step_major step_minor label_minor
## 3 fit.models_0_Random 1 2 myrandom_classfr
## 4 fit.models_0_Max.cor.Y.rcv.*X* 1 3 glmnet
## bgn end elapsed
## 3 120.619 128.245 7.627
## 4 128.246 NA NAret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y.rcv.1X1", type = glb_model_type, trainControl.method = "none",
train.method = "glmnet")),
indepVar = max_cor_y_x_vars, rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)## [1] "myfit_mdl: enter: 0.001000 secs"
## [1] "myfit_mdl: fitting model: Max.cor.Y.rcv.1X1###glmnet"
## [1] " indepVar: Q115611.fctr,Q113181.fctr"
## [1] "myfit_mdl: setup complete: 0.683000 secs"## Loading required package: glmnet## Loading required package: Matrix##
## Attaching package: 'Matrix'## The following object is masked from 'package:tidyr':
##
## expand## Loaded glmnet 2.0-5## Fitting alpha = 0.1, lambda = 0.00166 on full training set
## [1] "myfit_mdl: train complete: 1.411000 secs"
## alpha lambda
## 1 0.1 0.001656204
## Length Class Mode
## a0 48 -none- numeric
## beta 192 dgCMatrix S4
## df 48 -none- numeric
## dim 2 -none- numeric
## lambda 48 -none- numeric
## dev.ratio 48 -none- numeric
## nulldev 1 -none- numeric
## npasses 1 -none- numeric
## jerr 1 -none- numeric
## offset 1 -none- logical
## classnames 2 -none- character
## call 5 -none- call
## nobs 1 -none- numeric
## lambdaOpt 1 -none- numeric
## xNames 4 -none- character
## problemType 1 -none- character
## tuneValue 2 data.frame list
## obsLevels 2 -none- character
## [1] "min lambda > lambdaOpt:"
## (Intercept) Q113181.fctrNo Q113181.fctrYes Q115611.fctrNo
## 0.3053858 -0.2963546 0.4135322 -0.2362299
## Q115611.fctrYes
## 0.3448103
## [1] "max lambda < lambdaOpt:"
## [1] "Feats mismatch between coefs_left & rght:"
## [1] "(Intercept)" "Q113181.fctrNo" "Q113181.fctrYes" "Q115611.fctrNo"
## [5] "Q115611.fctrYes"
## [1] "myfit_mdl: train diagnostics complete: 1.518000 secs"
## Prediction
## Reference D R
## D 379 445
## R 306 827
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 6.162494e-01 1.943425e-01 5.942872e-01 6.378625e-01 5.789474e-01
## AccuracyPValue McnemarPValue
## 4.295434e-04 4.761268e-07
## Prediction
## Reference D R
## D 0 214
## R 0 288
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 5.737052e-01 0.000000e+00 5.291204e-01 6.174170e-01 5.737052e-01
## AccuracyPValue McnemarPValue
## 5.188758e-01 5.017792e-48
## [1] "myfit_mdl: predict complete: 7.108000 secs"
## id feats max.nTuningRuns
## 1 Max.cor.Y.rcv.1X1###glmnet Q115611.fctr,Q113181.fctr 0
## min.elapsedtime.everything min.elapsedtime.final max.AUCpROC.fit
## 1 0.721 0.028 0.5771183
## max.Sens.fit max.Spec.fit max.AUCROCR.fit opt.prob.threshold.fit
## 1 0.3519417 0.8022948 0.6256871 0.55
## max.f.score.fit max.Accuracy.fit max.AccuracyLower.fit
## 1 0.6877339 0.6162494 0.5942872
## max.AccuracyUpper.fit max.Kappa.fit max.AUCpROC.OOB max.Sens.OOB
## 1 0.6378625 0.1943425 0.5338785 0.317757
## max.Spec.OOB max.AUCROCR.OOB opt.prob.threshold.OOB max.f.score.OOB
## 1 0.75 0.5592306 0.4 0.7291139
## max.Accuracy.OOB max.AccuracyLower.OOB max.AccuracyUpper.OOB
## 1 0.5737052 0.5291204 0.617417
## max.Kappa.OOB
## 1 0
## [1] "myfit_mdl: exit: 7.177000 secs"if (glbMdlCheckRcv) {
# rcv_n_folds == 1 & rcv_n_repeats > 1 crashes
for (rcv_n_folds in seq(3, glb_rcv_n_folds + 2, 2))
for (rcv_n_repeats in seq(1, glb_rcv_n_repeats + 2, 2)) {
# Experiment specific code to avoid caret crash
# lcl_tune_models_df <- rbind(data.frame()
# ,data.frame(method = "glmnet", parameter = "alpha",
# vals = "0.100 0.325 0.550 0.775 1.000")
# ,data.frame(method = "glmnet", parameter = "lambda",
# vals = "9.342e-02")
# )
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst =
list(
id.prefix = paste0("Max.cor.Y.rcv.", rcv_n_folds, "X", rcv_n_repeats),
type = glb_model_type,
# tune.df = lcl_tune_models_df,
trainControl.method = "repeatedcv",
trainControl.number = rcv_n_folds,
trainControl.repeats = rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
train.method = "glmnet", train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize)),
indepVar = max_cor_y_x_vars, rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
}
# Add parallel coordinates graph of glb_models_df[, glbMdlMetricsEval] to evaluate cv parameters
tmp_models_cols <- c("id", "max.nTuningRuns",
glbMdlMetricsEval[glbMdlMetricsEval %in% names(glb_models_df)],
grep("opt.", names(glb_models_df), fixed = TRUE, value = TRUE))
print(myplot_parcoord(obs_df = subset(glb_models_df,
grepl("Max.cor.Y.rcv.", id, fixed = TRUE),
select = -feats)[, tmp_models_cols],
id_var = "id"))
}
# Useful for stacking decisions
# fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
# paste0("fit.models_0_", "Max.cor.Y[rcv.1X1.cp.0|]"), major.inc = FALSE,
# label.minor = "rpart")
#
# ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
# id.prefix = "Max.cor.Y.rcv.1X1.cp.0", type = glb_model_type, trainControl.method = "none",
# train.method = "rpart",
# tune.df=data.frame(method="rpart", parameter="cp", min=0.0, max=0.0, by=0.1))),
# indepVar=max_cor_y_x_vars, rsp_var=glb_rsp_var,
# fit_df=glbObsFit, OOB_df=glbObsOOB)
#stop(here"); glb2Sav(); all.equal(glb_models_df, sav_models_df)
# if (glb_is_regression || glb_is_binomial) # For multinomials this model will be run next by default
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y",
type = glb_model_type, trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds,
trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = "rpart")),
indepVar = max_cor_y_x_vars, rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)## [1] "myfit_mdl: enter: 0.001000 secs"
## [1] "myfit_mdl: fitting model: Max.cor.Y##rcv#rpart"
## [1] " indepVar: Q115611.fctr,Q113181.fctr"
## [1] "myfit_mdl: setup complete: 0.674000 secs"## Loading required package: rpart## Aggregating results
## Selecting tuning parameters
## Fitting cp = 0.0105 on full training set
## [1] "myfit_mdl: train complete: 2.096000 secs"## Loading required package: rpart.plot
## Call:
## rpart(formula = .outcome ~ ., control = list(minsplit = 20, minbucket = 7,
## cp = 0, maxcompete = 4, maxsurrogate = 5, usesurrogate = 2,
## surrogatestyle = 0, maxdepth = 30, xval = 0))
## n= 1957
##
## CP nsplit rel error
## 1 0.04186893 0 1.0000000
## 2 0.01046723 2 0.9162621
##
## Variable importance
## Q113181.fctrYes Q113181.fctrNo Q115611.fctrNo Q115611.fctrYes
## 41 29 19 11
##
## Node number 1: 1957 observations, complexity param=0.04186893
## predicted class=R expected loss=0.4210526 P(node) =1
## class counts: 824 1133
## probabilities: 0.421 0.579
## left son=2 (1207 obs) right son=3 (750 obs)
## Primary splits:
## Q113181.fctrYes < 0.5 to the left, improve=26.84038, (0 missing)
## Q113181.fctrNo < 0.5 to the right, improve=23.63967, (0 missing)
## Q115611.fctrYes < 0.5 to the left, improve=19.10792, (0 missing)
## Q115611.fctrNo < 0.5 to the right, improve=16.37764, (0 missing)
## Surrogate splits:
## Q113181.fctrNo < 0.5 to the right, agree=0.852, adj=0.613, (0 split)
##
## Node number 2: 1207 observations, complexity param=0.04186893
## predicted class=R expected loss=0.4863297 P(node) =0.6167603
## class counts: 587 620
## probabilities: 0.486 0.514
## left son=4 (599 obs) right son=5 (608 obs)
## Primary splits:
## Q115611.fctrNo < 0.5 to the right, improve=12.07893, (0 missing)
## Q115611.fctrYes < 0.5 to the left, improve=10.61765, (0 missing)
## Q113181.fctrNo < 0.5 to the right, improve= 2.33422, (0 missing)
## Surrogate splits:
## Q115611.fctrYes < 0.5 to the left, agree=0.794, adj=0.584, (0 split)
## Q113181.fctrNo < 0.5 to the right, agree=0.596, adj=0.185, (0 split)
##
## Node number 3: 750 observations
## predicted class=R expected loss=0.316 P(node) =0.3832397
## class counts: 237 513
## probabilities: 0.316 0.684
##
## Node number 4: 599 observations
## predicted class=D expected loss=0.442404 P(node) =0.3060807
## class counts: 334 265
## probabilities: 0.558 0.442
##
## Node number 5: 608 observations
## predicted class=R expected loss=0.4161184 P(node) =0.3106796
## class counts: 253 355
## probabilities: 0.416 0.584
##
## n= 1957
##
## node), split, n, loss, yval, (yprob)
## * denotes terminal node
##
## 1) root 1957 824 R (0.4210526 0.5789474)
## 2) Q113181.fctrYes< 0.5 1207 587 R (0.4863297 0.5136703)
## 4) Q115611.fctrNo>=0.5 599 265 D (0.5575960 0.4424040) *
## 5) Q115611.fctrNo< 0.5 608 253 R (0.4161184 0.5838816) *
## 3) Q113181.fctrYes>=0.5 750 237 R (0.3160000 0.6840000) *
## [1] "myfit_mdl: train diagnostics complete: 2.910000 secs"
## [1] "mypredict_mdl: maxMetricDf:"
## threshold f.score accuracy
## 10 0.45 0.6969089 0.6142054
## 11 0.50 0.6969089 0.6142054
## 12 0.55 0.6969089 0.6142054
## Prediction
## Reference D R
## D 334 490
## R 265 868
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 6.142054e-01 1.780783e-01 5.922249e-01 6.358431e-01 5.789474e-01
## AccuracyPValue McnemarPValue
## 8.214160e-04 3.573784e-16
## Prediction
## Reference D R
## D 0 214
## R 0 288
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 5.737052e-01 0.000000e+00 5.291204e-01 6.174170e-01 5.737052e-01
## AccuracyPValue McnemarPValue
## 5.188758e-01 5.017792e-48
## [1] "myfit_mdl: predict complete: 8.849000 secs"
## id feats max.nTuningRuns
## 1 Max.cor.Y##rcv#rpart Q115611.fctr,Q113181.fctr 5
## min.elapsedtime.everything min.elapsedtime.final max.AUCpROC.fit
## 1 1.415 0.015 0.5857237
## max.Sens.fit max.Spec.fit max.AUCROCR.fit opt.prob.threshold.fit
## 1 0.4053398 0.7661077 0.6101745 0.5
## max.f.score.fit max.Accuracy.fit max.AccuracyLower.fit
## 1 0.6969089 0.6104535 0.5922249
## max.AccuracyUpper.fit max.Kappa.fit max.AUCpROC.OOB max.Sens.OOB
## 1 0.6358431 0.177199 0.5334729 0.3551402
## max.Spec.OOB max.AUCROCR.OOB opt.prob.threshold.OOB max.f.score.OOB
## 1 0.7118056 0.5325318 0.4 0.7291139
## max.Accuracy.OOB max.AccuracyLower.OOB max.AccuracyUpper.OOB
## 1 0.5737052 0.5291204 0.617417
## max.Kappa.OOB max.AccuracySD.fit max.KappaSD.fit
## 1 0 0.01616114 0.02629543
## [1] "myfit_mdl: exit: 8.911000 secs"if ((length(glbFeatsDateTime) > 0) &&
(sum(grepl(paste(names(glbFeatsDateTime), "\\.day\\.minutes\\.poly\\.", sep = ""),
names(glbObsAll))) > 0)) {
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Max.cor.Y.Time.Poly"), major.inc = FALSE,
label.minor = "glmnet")
indepVars <- c(max_cor_y_x_vars,
grep(paste(names(glbFeatsDateTime), "\\.day\\.minutes\\.poly\\.", sep = ""),
names(glbObsAll), value = TRUE))
indepVars <- myadjustInteractionFeats(glb_feats_df, indepVars)
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y.Time.Poly",
type = glb_model_type, trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds, trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = "glmnet")),
indepVar = indepVars,
rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
}
if ((length(glbFeatsDateTime) > 0) &&
(sum(grepl(paste(names(glbFeatsDateTime), "\\.last[[:digit:]]", sep = ""),
names(glbObsAll))) > 0)) {
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Max.cor.Y.Time.Lag"), major.inc = FALSE,
label.minor = "glmnet")
indepVars <- c(max_cor_y_x_vars,
grep(paste(names(glbFeatsDateTime), "\\.last[[:digit:]]", sep = ""),
names(glbObsAll), value = TRUE))
indepVars <- myadjustInteractionFeats(glb_feats_df, indepVars)
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y.Time.Lag",
type = glb_model_type,
tune.df = glbMdlTuneParams,
trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds, trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = "glmnet")),
indepVar = indepVars,
rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
}
if (length(glbFeatsText) > 0) {
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Txt.*"), major.inc = FALSE,
label.minor = "glmnet")
indepVars <- c(max_cor_y_x_vars)
for (txtFeat in names(glbFeatsText))
indepVars <- union(indepVars,
grep(paste(str_to_upper(substr(txtFeat, 1, 1)), "\\.(?!([T|P]\\.))", sep = ""),
names(glbObsAll), perl = TRUE, value = TRUE))
indepVars <- myadjustInteractionFeats(glb_feats_df, indepVars)
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y.Text.nonTP",
type = glb_model_type,
tune.df = glbMdlTuneParams,
trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds, trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = "glmnet")),
indepVar = indepVars,
rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
indepVars <- c(max_cor_y_x_vars)
for (txtFeat in names(glbFeatsText))
indepVars <- union(indepVars,
grep(paste(str_to_upper(substr(txtFeat, 1, 1)), "\\.T\\.", sep = ""),
names(glbObsAll), perl = TRUE, value = TRUE))
indepVars <- myadjustInteractionFeats(glb_feats_df, indepVars)
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y.Text.onlyT",
type = glb_model_type,
tune.df = glbMdlTuneParams,
trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds, trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = "glmnet")),
indepVar = indepVars,
rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
indepVars <- c(max_cor_y_x_vars)
for (txtFeat in names(glbFeatsText))
indepVars <- union(indepVars,
grep(paste(str_to_upper(substr(txtFeat, 1, 1)), "\\.P\\.", sep = ""),
names(glbObsAll), perl = TRUE, value = TRUE))
indepVars <- myadjustInteractionFeats(glb_feats_df, indepVars)
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y.Text.onlyP",
type = glb_model_type,
tune.df = glbMdlTuneParams,
trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds, trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = "glmnet")),
indepVar = indepVars,
rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
}
# Interactions.High.cor.Y
if (length(int_feats <- setdiff(setdiff(unique(glb_feats_df$cor.high.X), NA),
subset(glb_feats_df, nzv)$id)) > 0) {
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Interact.High.cor.Y"), major.inc = FALSE,
label.minor = "glmnet")
ret_lst <- myfit_mdl(mdl_specs_lst=myinit_mdl_specs_lst(mdl_specs_lst=list(
id.prefix="Interact.High.cor.Y",
type=glb_model_type, trainControl.method="repeatedcv",
trainControl.number=glb_rcv_n_folds, trainControl.repeats=glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method="glmnet")),
indepVar=c(max_cor_y_x_vars, paste(max_cor_y_x_vars[1], int_feats, sep=":")),
rsp_var=glb_rsp_var,
fit_df=glbObsFit, OOB_df=glbObsOOB)
}
# Low.cor.X
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Low.cor.X"), major.inc = FALSE,
label.minor = "glmnet")## label step_major step_minor label_minor bgn
## 4 fit.models_0_Max.cor.Y.rcv.*X* 1 3 glmnet 128.246
## 5 fit.models_0_Low.cor.X 1 4 glmnet 144.381
## end elapsed
## 4 144.38 16.134
## 5 NA NAindepVar <- mygetIndepVar(glb_feats_df)
indepVar <- setdiff(indepVar, unique(glb_feats_df$cor.high.X))
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Low.cor.X",
type = glb_model_type,
tune.df = glbMdlTuneParams,
trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds, trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = "glmnet")),
indepVar = indepVar, rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)## [1] "myfit_mdl: enter: 0.001000 secs"
## [1] "myfit_mdl: fitting model: Low.cor.X##rcv#glmnet"
## [1] " indepVar: Q115611.fctr,Q113181.fctr,Q98197.fctr,Q116881.fctr,Q108855.fctr,Q106272.fctr,Q122771.fctr,Q123621.fctr,Q106388.fctr,Q110740.fctr,Q122769.fctr,Q120472.fctr,Q101596.fctr,Q119334.fctr,Q114152.fctr,Q98869.fctr,Q115899.fctr,Q116797.fctr,Q118232.fctr,Gender.fctr,Q105655.fctr,Q99480.fctr,Q123464.fctr,Q120650.fctr,Q122120.fctr,Q107869.fctr,Q120014.fctr,Q102289.fctr,Income.fctr,Q122770.fctr,Q111580.fctr,Q116601.fctr,Q117186.fctr,Q106993.fctr,Q112270.fctr,Q101162.fctr,Q108856.fctr,Q117193.fctr,Q116441.fctr,Q119851.fctr,Q111848.fctr,Q98578.fctr,Q118892.fctr,Q114386.fctr,Q120978.fctr,Q112512.fctr,Q102674.fctr,Q96024.fctr,Q108950.fctr,Q115610.fctr,YOB.Age.fctr,Q112478.fctr,Q116197.fctr,Q124742.fctr,Q106389.fctr,Edn.fctr,Q118117.fctr,Q100562.fctr,Q107491.fctr,Q116448.fctr,Q108754.fctr,Q116953.fctr,Q115602.fctr,Q118233.fctr,Q120012.fctr,Q118237.fctr,Q99581.fctr,.rnorm,Q120194.fctr,Q115777.fctr,Q106997.fctr,Q100680.fctr,Q113584.fctr,Q108343.fctr,Q121700.fctr,Q105840.fctr,Q120379.fctr,Q103293.fctr,Q124122.fctr,Q109367.fctr,Q113992.fctr,Q121699.fctr,Q121011.fctr,Q114748.fctr,Q106042.fctr,Q111220.fctr,Q114517.fctr,Q102687.fctr,Q102906.fctr,Q98078.fctr,Q115390.fctr,Q102089.fctr,Q100010.fctr,Q99982.fctr,Q113583.fctr,Q108342.fctr,Q104996.fctr,Q119650.fctr,Q100689.fctr,Q108617.fctr,Q115195.fctr,Q99716.fctr,Q101163.fctr,Q98059.fctr,Q114961.fctr,Hhold.fctr,Hhold.fctr:.clusterid.fctr,YOB.Age.fctr:YOB.Age.dff"
## [1] "myfit_mdl: setup complete: 0.692000 secs"
## Aggregating results
## Selecting tuning parameters
## Fitting alpha = 0.55, lambda = 0.0357 on full training set
## [1] "myfit_mdl: train complete: 16.276000 secs"## Warning in myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst
## = list(id.prefix = "Low.cor.X", : model's bestTune found at an extreme of
## tuneGrid for parameter: lambda
## Length Class Mode
## a0 84 -none- numeric
## beta 21840 dgCMatrix S4
## df 84 -none- numeric
## dim 2 -none- numeric
## lambda 84 -none- numeric
## dev.ratio 84 -none- numeric
## nulldev 1 -none- numeric
## npasses 1 -none- numeric
## jerr 1 -none- numeric
## offset 1 -none- logical
## classnames 2 -none- character
## call 5 -none- call
## nobs 1 -none- numeric
## lambdaOpt 1 -none- numeric
## xNames 260 -none- character
## problemType 1 -none- character
## tuneValue 2 data.frame list
## obsLevels 2 -none- character
## [1] "min lambda > lambdaOpt:"
## (Intercept) Hhold.fctrMKy Hhold.fctrPKn
## 0.221440531 0.088740320 -0.363049495
## Hhold.fctrPKy Income.fctr.Q Income.fctr.C
## -0.066620973 0.023323191 0.013246595
## Q100562.fctrNo Q101163.fctrDad Q106272.fctrYes
## -0.037681183 0.100162253 0.076786887
## Q106997.fctrGr Q110740.fctrPC Q113181.fctrNo
## 0.060299822 0.043782927 -0.176988082
## Q113181.fctrYes Q115611.fctrNo Q115611.fctrYes
## 0.230691777 -0.159469858 0.181404742
## Q115899.fctrCs Q116881.fctrHappy Q116881.fctrRight
## -0.021861438 -0.006195520 0.087679839
## Q119650.fctrGiving Q119650.fctrReceiving Q98197.fctrNo
## 0.015633046 -0.005378502 -0.138631965
## Q98869.fctrNo Q99480.fctrNo
## -0.012566215 -0.016768438
## [1] "max lambda < lambdaOpt:"
## (Intercept) Hhold.fctrMKy
## 0.216762556 0.094569421
## Hhold.fctrPKn Hhold.fctrPKy
## -0.403641466 -0.147928827
## Hhold.fctrSKy Income.fctr.Q
## -0.028492249 0.046046298
## Income.fctr.C Q100562.fctrNo
## 0.037396969 -0.058607469
## Q101163.fctrDad Q106272.fctrYes
## 0.113053847 0.086518373
## Q106997.fctrGr Q106997.fctrYy
## 0.074861094 -0.007176625
## Q110740.fctrPC Q113181.fctrNo
## 0.057142311 -0.182381789
## Q113181.fctrYes Q115611.fctrNo
## 0.232846900 -0.165108486
## Q115611.fctrYes Q115899.fctrCs
## 0.187103110 -0.036662653
## Q116881.fctrHappy Q116881.fctrRight
## -0.017190537 0.093784522
## Q119650.fctrGiving Q119650.fctrReceiving
## 0.026231177 -0.011093638
## Q98197.fctrNo Q98869.fctrNo
## -0.145180735 -0.027405096
## Q99480.fctrNo Hhold.fctrMKy:.clusterid.fctr4
## -0.027633363 0.009349452
## [1] "myfit_mdl: train diagnostics complete: 16.956000 secs"
## Prediction
## Reference D R
## D 266 558
## R 161 972
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 6.326009e-01 1.934227e-01 6.108001e-01 6.540036e-01 5.789474e-01
## AccuracyPValue McnemarPValue
## 7.327469e-07 2.345270e-49
## [1] "mypredict_mdl: maxMetricDf:"
## threshold f.score accuracy
## 1 0.00 0.7291139 0.5737052
## 2 0.05 0.7291139 0.5737052
## 3 0.10 0.7291139 0.5737052
## 4 0.15 0.7291139 0.5737052
## 5 0.20 0.7291139 0.5737052
## 6 0.25 0.7291139 0.5737052
## 7 0.30 0.7291139 0.5737052
## 8 0.35 0.7291139 0.5737052
## 9 0.40 0.7291139 0.5737052
## 10 0.45 0.7213542 0.5737052
## 12 0.55 0.6409396 0.5737052
## Prediction
## Reference D R
## D 11 203
## R 11 277
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 5.737052e-01 1.492811e-02 5.291204e-01 6.174170e-01 5.737052e-01
## AccuracyPValue McnemarPValue
## 5.188758e-01 5.835606e-39
## [1] "myfit_mdl: predict complete: 26.440000 secs"
## id
## 1 Low.cor.X##rcv#glmnet
## feats
## 1 Q115611.fctr,Q113181.fctr,Q98197.fctr,Q116881.fctr,Q108855.fctr,Q106272.fctr,Q122771.fctr,Q123621.fctr,Q106388.fctr,Q110740.fctr,Q122769.fctr,Q120472.fctr,Q101596.fctr,Q119334.fctr,Q114152.fctr,Q98869.fctr,Q115899.fctr,Q116797.fctr,Q118232.fctr,Gender.fctr,Q105655.fctr,Q99480.fctr,Q123464.fctr,Q120650.fctr,Q122120.fctr,Q107869.fctr,Q120014.fctr,Q102289.fctr,Income.fctr,Q122770.fctr,Q111580.fctr,Q116601.fctr,Q117186.fctr,Q106993.fctr,Q112270.fctr,Q101162.fctr,Q108856.fctr,Q117193.fctr,Q116441.fctr,Q119851.fctr,Q111848.fctr,Q98578.fctr,Q118892.fctr,Q114386.fctr,Q120978.fctr,Q112512.fctr,Q102674.fctr,Q96024.fctr,Q108950.fctr,Q115610.fctr,YOB.Age.fctr,Q112478.fctr,Q116197.fctr,Q124742.fctr,Q106389.fctr,Edn.fctr,Q118117.fctr,Q100562.fctr,Q107491.fctr,Q116448.fctr,Q108754.fctr,Q116953.fctr,Q115602.fctr,Q118233.fctr,Q120012.fctr,Q118237.fctr,Q99581.fctr,.rnorm,Q120194.fctr,Q115777.fctr,Q106997.fctr,Q100680.fctr,Q113584.fctr,Q108343.fctr,Q121700.fctr,Q105840.fctr,Q120379.fctr,Q103293.fctr,Q124122.fctr,Q109367.fctr,Q113992.fctr,Q121699.fctr,Q121011.fctr,Q114748.fctr,Q106042.fctr,Q111220.fctr,Q114517.fctr,Q102687.fctr,Q102906.fctr,Q98078.fctr,Q115390.fctr,Q102089.fctr,Q100010.fctr,Q99982.fctr,Q113583.fctr,Q108342.fctr,Q104996.fctr,Q119650.fctr,Q100689.fctr,Q108617.fctr,Q115195.fctr,Q99716.fctr,Q101163.fctr,Q98059.fctr,Q114961.fctr,Hhold.fctr,Hhold.fctr:.clusterid.fctr,YOB.Age.fctr:YOB.Age.dff
## max.nTuningRuns min.elapsedtime.everything min.elapsedtime.final
## 1 25 15.497 1.772
## max.AUCpROC.fit max.Sens.fit max.Spec.fit max.AUCROCR.fit
## 1 0.5903575 0.3228155 0.8578994 0.661983
## opt.prob.threshold.fit max.f.score.fit max.Accuracy.fit
## 1 0.5 0.7300038 0.6050093
## max.AccuracyLower.fit max.AccuracyUpper.fit max.Kappa.fit
## 1 0.6108001 0.6540036 0.128624
## max.AUCpROC.OOB max.Sens.OOB max.Spec.OOB max.AUCROCR.OOB
## 1 0.5091186 0.2196262 0.7986111 0.5816378
## opt.prob.threshold.OOB max.f.score.OOB max.Accuracy.OOB
## 1 0.45 0.7213542 0.5737052
## max.AccuracyLower.OOB max.AccuracyUpper.OOB max.Kappa.OOB
## 1 0.5291204 0.617417 0.01492811
## max.AccuracySD.fit max.KappaSD.fit
## 1 0.01148221 0.02835557
## [1] "myfit_mdl: exit: 26.768000 secs"fit.models_0_chunk_df <-
myadd_chunk(fit.models_0_chunk_df, "fit.models_0_end", major.inc = FALSE,
label.minor = "teardown")## label step_major step_minor label_minor bgn end
## 5 fit.models_0_Low.cor.X 1 4 glmnet 144.381 171.189
## 6 fit.models_0_end 1 5 teardown 171.190 NA
## elapsed
## 5 26.809
## 6 NArm(ret_lst)
glb_chunks_df <- myadd_chunk(glb_chunks_df, "fit.models", major.inc = FALSE)## label step_major step_minor label_minor bgn end elapsed
## 14 fit.models 7 0 0 113.283 171.204 57.922
## 15 fit.models 7 1 1 171.205 NA NA```{r fit.models_1, cache=FALSE, fig.height=10, fig.width=15, eval=myevlChunk(glbChunks, glbOut$pfx)}
## label step_major step_minor label_minor bgn end elapsed
## 1 fit.models_1_bgn 1 0 setup 174.976 NA NA## label step_major step_minor label_minor bgn end
## 1 fit.models_1_bgn 1 0 setup 174.976 174.988
## 2 fit.models_1_All.X 1 1 setup 174.989 NA
## elapsed
## 1 0.012
## 2 NA
## label step_major step_minor label_minor bgn end
## 2 fit.models_1_All.X 1 1 setup 174.989 174.997
## 3 fit.models_1_All.X 1 2 glmnet 174.997 NA
## elapsed
## 2 0.008
## 3 NA
## [1] "myfit_mdl: enter: 0.001000 secs"
## [1] "myfit_mdl: fitting model: All.X##rcv#glmnet"
## [1] " indepVar: Q115611.fctr,Q113181.fctr,Q98197.fctr,Q116881.fctr,Q108855.fctr,Q106272.fctr,Q122771.fctr,Q123621.fctr,Q106388.fctr,Q110740.fctr,Q122769.fctr,Q120472.fctr,Q101596.fctr,Q119334.fctr,Q114152.fctr,Q98869.fctr,Q115899.fctr,Q116797.fctr,Q118232.fctr,Gender.fctr,Q105655.fctr,Q99480.fctr,Q123464.fctr,Q120650.fctr,Q122120.fctr,Q107869.fctr,Q120014.fctr,Q102289.fctr,Income.fctr,Q122770.fctr,Q111580.fctr,Q116601.fctr,Q117186.fctr,Q106993.fctr,Q112270.fctr,Q101162.fctr,Q108856.fctr,Q117193.fctr,Q116441.fctr,Q119851.fctr,Q111848.fctr,Q98578.fctr,Q118892.fctr,Q114386.fctr,Q120978.fctr,Q112512.fctr,Q102674.fctr,Q96024.fctr,Q108950.fctr,Q115610.fctr,YOB.Age.fctr,Q112478.fctr,Q116197.fctr,Q124742.fctr,Q106389.fctr,Edn.fctr,Q118117.fctr,Q100562.fctr,Q107491.fctr,Q116448.fctr,Q108754.fctr,Q116953.fctr,Q115602.fctr,Q118233.fctr,Q120012.fctr,Q118237.fctr,Q99581.fctr,.rnorm,Q120194.fctr,Q115777.fctr,Q106997.fctr,Q100680.fctr,Q113584.fctr,Q108343.fctr,Q121700.fctr,Q105840.fctr,Q120379.fctr,Q103293.fctr,Q124122.fctr,Q109367.fctr,Q113992.fctr,Q121699.fctr,Q121011.fctr,Q114748.fctr,Q106042.fctr,Q111220.fctr,Q114517.fctr,Q102687.fctr,Q102906.fctr,Q98078.fctr,Q115390.fctr,Q102089.fctr,Q100010.fctr,Q99982.fctr,Q113583.fctr,Q108342.fctr,Q104996.fctr,Q119650.fctr,Q100689.fctr,Q108617.fctr,Q115195.fctr,Q99716.fctr,Q101163.fctr,Q98059.fctr,Q114961.fctr,Hhold.fctr,Hhold.fctr:.clusterid.fctr,YOB.Age.fctr:YOB.Age.dff"
## [1] "myfit_mdl: setup complete: 0.709000 secs"
## Aggregating results
## Selecting tuning parameters
## Fitting alpha = 0.325, lambda = 0.0637 on full training set
## [1] "myfit_mdl: train complete: 16.547000 secs"
## Length Class Mode
## a0 86 -none- numeric
## beta 22360 dgCMatrix S4
## df 86 -none- numeric
## dim 2 -none- numeric
## lambda 86 -none- numeric
## dev.ratio 86 -none- numeric
## nulldev 1 -none- numeric
## npasses 1 -none- numeric
## jerr 1 -none- numeric
## offset 1 -none- logical
## classnames 2 -none- character
## call 5 -none- call
## nobs 1 -none- numeric
## lambdaOpt 1 -none- numeric
## xNames 260 -none- character
## problemType 1 -none- character
## tuneValue 2 data.frame list
## obsLevels 2 -none- character
## [1] "min lambda > lambdaOpt:"
## (Intercept) Hhold.fctrMKy Hhold.fctrPKn
## 0.2406428928 0.0762870273 -0.2953396040
## Q100562.fctrNo Q101163.fctrDad Q106272.fctrYes
## -0.0110508029 0.0800696434 0.0664514859
## Q106997.fctrGr Q110740.fctrPC Q113181.fctrNo
## 0.0347221725 0.0274085076 -0.1636826446
## Q113181.fctrYes Q115611.fctrNo Q115611.fctrYes
## 0.2111681078 -0.1409573482 0.1699102327
## Q115899.fctrCs Q116881.fctrHappy Q116881.fctrRight
## -0.0047139261 -0.0001640877 0.0711299222
## Q119650.fctrGiving Q98197.fctrNo Q98869.fctrNo
## 0.0099743987 -0.1280674998 -0.0064004001
## Q99480.fctrNo
## -0.0105142415
## [1] "max lambda < lambdaOpt:"
## (Intercept) Hhold.fctrMKy Hhold.fctrPKn
## 0.231137831 0.084903152 -0.334415212
## Hhold.fctrPKy Income.fctr.Q Income.fctr.C
## -0.065222397 0.020496301 0.010335205
## Q100562.fctrNo Q101163.fctrDad Q106272.fctrYes
## -0.032098432 0.093074498 0.075016818
## Q106997.fctrGr Q110740.fctrPC Q113181.fctrNo
## 0.053588195 0.040691709 -0.170206282
## Q113181.fctrYes Q115611.fctrNo Q115611.fctrYes
## 0.215390053 -0.148615954 0.174916163
## Q115899.fctrCs Q116881.fctrHappy Q116881.fctrRight
## -0.019155211 -0.011048021 0.078702675
## Q119650.fctrGiving Q119650.fctrReceiving Q98197.fctrNo
## 0.019371664 -0.005670503 -0.135056904
## Q98869.fctrNo Q99480.fctrNo
## -0.019568656 -0.021088646
## [1] "myfit_mdl: train diagnostics complete: 17.191000 secs"
## Prediction
## Reference D R
## D 247 577
## R 143 990
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 6.320899e-01 1.869725e-01 6.102837e-01 6.534996e-01 5.789474e-01
## AccuracyPValue McnemarPValue
## 9.237623e-07 1.402889e-58
## Prediction
## Reference D R
## D 97 117
## R 94 194
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 0.5796813 0.1286586 0.5351418 0.6232769 0.5737052
## AccuracyPValue McnemarPValue
## 0.4115799 0.1298883
## [1] "myfit_mdl: predict complete: 26.950000 secs"
## id
## 1 All.X##rcv#glmnet
## feats
## 1 Q115611.fctr,Q113181.fctr,Q98197.fctr,Q116881.fctr,Q108855.fctr,Q106272.fctr,Q122771.fctr,Q123621.fctr,Q106388.fctr,Q110740.fctr,Q122769.fctr,Q120472.fctr,Q101596.fctr,Q119334.fctr,Q114152.fctr,Q98869.fctr,Q115899.fctr,Q116797.fctr,Q118232.fctr,Gender.fctr,Q105655.fctr,Q99480.fctr,Q123464.fctr,Q120650.fctr,Q122120.fctr,Q107869.fctr,Q120014.fctr,Q102289.fctr,Income.fctr,Q122770.fctr,Q111580.fctr,Q116601.fctr,Q117186.fctr,Q106993.fctr,Q112270.fctr,Q101162.fctr,Q108856.fctr,Q117193.fctr,Q116441.fctr,Q119851.fctr,Q111848.fctr,Q98578.fctr,Q118892.fctr,Q114386.fctr,Q120978.fctr,Q112512.fctr,Q102674.fctr,Q96024.fctr,Q108950.fctr,Q115610.fctr,YOB.Age.fctr,Q112478.fctr,Q116197.fctr,Q124742.fctr,Q106389.fctr,Edn.fctr,Q118117.fctr,Q100562.fctr,Q107491.fctr,Q116448.fctr,Q108754.fctr,Q116953.fctr,Q115602.fctr,Q118233.fctr,Q120012.fctr,Q118237.fctr,Q99581.fctr,.rnorm,Q120194.fctr,Q115777.fctr,Q106997.fctr,Q100680.fctr,Q113584.fctr,Q108343.fctr,Q121700.fctr,Q105840.fctr,Q120379.fctr,Q103293.fctr,Q124122.fctr,Q109367.fctr,Q113992.fctr,Q121699.fctr,Q121011.fctr,Q114748.fctr,Q106042.fctr,Q111220.fctr,Q114517.fctr,Q102687.fctr,Q102906.fctr,Q98078.fctr,Q115390.fctr,Q102089.fctr,Q100010.fctr,Q99982.fctr,Q113583.fctr,Q108342.fctr,Q104996.fctr,Q119650.fctr,Q100689.fctr,Q108617.fctr,Q115195.fctr,Q99716.fctr,Q101163.fctr,Q98059.fctr,Q114961.fctr,Hhold.fctr,Hhold.fctr:.clusterid.fctr,YOB.Age.fctr:YOB.Age.dff
## max.nTuningRuns min.elapsedtime.everything min.elapsedtime.final
## 1 25 15.75 1.798
## max.AUCpROC.fit max.Sens.fit max.Spec.fit max.AUCROCR.fit
## 1 0.5867718 0.2997573 0.8737864 0.6590272
## opt.prob.threshold.fit max.f.score.fit max.Accuracy.fit
## 1 0.5 0.7333333 0.6055195
## max.AccuracyLower.fit max.AccuracyUpper.fit max.Kappa.fit
## 1 0.6102837 0.6534996 0.1238626
## max.AUCpROC.OOB max.Sens.OOB max.Spec.OOB max.AUCROCR.OOB
## 1 0.5067173 0.2009346 0.8125 0.5801856
## opt.prob.threshold.OOB max.f.score.OOB max.Accuracy.OOB
## 1 0.55 0.6477462 0.5796813
## max.AccuracyLower.OOB max.AccuracyUpper.OOB max.Kappa.OOB
## 1 0.5351418 0.6232769 0.1286586
## max.AccuracySD.fit max.KappaSD.fit
## 1 0.0117432 0.02938213
## [1] "myfit_mdl: exit: 27.232000 secs"## label step_major step_minor label_minor bgn end
## 3 fit.models_1_All.X 1 2 glmnet 174.997 202.254
## 4 fit.models_1_preProc 1 3 preProc 202.254 NA
## elapsed
## 3 27.257
## 4 NA## Loading required package: gdata## gdata: read.xls support for 'XLS' (Excel 97-2004) files ENABLED.## ## gdata: read.xls support for 'XLSX' (Excel 2007+) files ENABLED.##
## Attaching package: 'gdata'## The following objects are masked from 'package:dplyr':
##
## combine, first, last## The following object is masked from 'package:stats':
##
## nobs## The following object is masked from 'package:utils':
##
## object.size## id
## All.X##rcv#glmnet All.X##rcv#glmnet
## Low.cor.X##rcv#glmnet Low.cor.X##rcv#glmnet
## Max.cor.Y.rcv.1X1###glmnet Max.cor.Y.rcv.1X1###glmnet
## Max.cor.Y##rcv#rpart Max.cor.Y##rcv#rpart
## Random###myrandom_classfr Random###myrandom_classfr
## feats
## All.X##rcv#glmnet Q115611.fctr,Q113181.fctr,Q98197.fctr,Q116881.fctr,Q108855.fctr,Q106272.fctr,Q122771.fctr,Q123621.fctr,Q106388.fctr,Q110740.fctr,Q122769.fctr,Q120472.fctr,Q101596.fctr,Q119334.fctr,Q114152.fctr,Q98869.fctr,Q115899.fctr,Q116797.fctr,Q118232.fctr,Gender.fctr,Q105655.fctr,Q99480.fctr,Q123464.fctr,Q120650.fctr,Q122120.fctr,Q107869.fctr,Q120014.fctr,Q102289.fctr,Income.fctr,Q122770.fctr,Q111580.fctr,Q116601.fctr,Q117186.fctr,Q106993.fctr,Q112270.fctr,Q101162.fctr,Q108856.fctr,Q117193.fctr,Q116441.fctr,Q119851.fctr,Q111848.fctr,Q98578.fctr,Q118892.fctr,Q114386.fctr,Q120978.fctr,Q112512.fctr,Q102674.fctr,Q96024.fctr,Q108950.fctr,Q115610.fctr,YOB.Age.fctr,Q112478.fctr,Q116197.fctr,Q124742.fctr,Q106389.fctr,Edn.fctr,Q118117.fctr,Q100562.fctr,Q107491.fctr,Q116448.fctr,Q108754.fctr,Q116953.fctr,Q115602.fctr,Q118233.fctr,Q120012.fctr,Q118237.fctr,Q99581.fctr,.rnorm,Q120194.fctr,Q115777.fctr,Q106997.fctr,Q100680.fctr,Q113584.fctr,Q108343.fctr,Q121700.fctr,Q105840.fctr,Q120379.fctr,Q103293.fctr,Q124122.fctr,Q109367.fctr,Q113992.fctr,Q121699.fctr,Q121011.fctr,Q114748.fctr,Q106042.fctr,Q111220.fctr,Q114517.fctr,Q102687.fctr,Q102906.fctr,Q98078.fctr,Q115390.fctr,Q102089.fctr,Q100010.fctr,Q99982.fctr,Q113583.fctr,Q108342.fctr,Q104996.fctr,Q119650.fctr,Q100689.fctr,Q108617.fctr,Q115195.fctr,Q99716.fctr,Q101163.fctr,Q98059.fctr,Q114961.fctr,Hhold.fctr,Hhold.fctr:.clusterid.fctr,YOB.Age.fctr:YOB.Age.dff
## Low.cor.X##rcv#glmnet Q115611.fctr,Q113181.fctr,Q98197.fctr,Q116881.fctr,Q108855.fctr,Q106272.fctr,Q122771.fctr,Q123621.fctr,Q106388.fctr,Q110740.fctr,Q122769.fctr,Q120472.fctr,Q101596.fctr,Q119334.fctr,Q114152.fctr,Q98869.fctr,Q115899.fctr,Q116797.fctr,Q118232.fctr,Gender.fctr,Q105655.fctr,Q99480.fctr,Q123464.fctr,Q120650.fctr,Q122120.fctr,Q107869.fctr,Q120014.fctr,Q102289.fctr,Income.fctr,Q122770.fctr,Q111580.fctr,Q116601.fctr,Q117186.fctr,Q106993.fctr,Q112270.fctr,Q101162.fctr,Q108856.fctr,Q117193.fctr,Q116441.fctr,Q119851.fctr,Q111848.fctr,Q98578.fctr,Q118892.fctr,Q114386.fctr,Q120978.fctr,Q112512.fctr,Q102674.fctr,Q96024.fctr,Q108950.fctr,Q115610.fctr,YOB.Age.fctr,Q112478.fctr,Q116197.fctr,Q124742.fctr,Q106389.fctr,Edn.fctr,Q118117.fctr,Q100562.fctr,Q107491.fctr,Q116448.fctr,Q108754.fctr,Q116953.fctr,Q115602.fctr,Q118233.fctr,Q120012.fctr,Q118237.fctr,Q99581.fctr,.rnorm,Q120194.fctr,Q115777.fctr,Q106997.fctr,Q100680.fctr,Q113584.fctr,Q108343.fctr,Q121700.fctr,Q105840.fctr,Q120379.fctr,Q103293.fctr,Q124122.fctr,Q109367.fctr,Q113992.fctr,Q121699.fctr,Q121011.fctr,Q114748.fctr,Q106042.fctr,Q111220.fctr,Q114517.fctr,Q102687.fctr,Q102906.fctr,Q98078.fctr,Q115390.fctr,Q102089.fctr,Q100010.fctr,Q99982.fctr,Q113583.fctr,Q108342.fctr,Q104996.fctr,Q119650.fctr,Q100689.fctr,Q108617.fctr,Q115195.fctr,Q99716.fctr,Q101163.fctr,Q98059.fctr,Q114961.fctr,Hhold.fctr,Hhold.fctr:.clusterid.fctr,YOB.Age.fctr:YOB.Age.dff
## Max.cor.Y.rcv.1X1###glmnet Q115611.fctr,Q113181.fctr
## Max.cor.Y##rcv#rpart Q115611.fctr,Q113181.fctr
## Random###myrandom_classfr .rnorm
## max.nTuningRuns min.elapsedtime.everything
## All.X##rcv#glmnet 25 15.750
## Low.cor.X##rcv#glmnet 25 15.497
## Max.cor.Y.rcv.1X1###glmnet 0 0.721
## Max.cor.Y##rcv#rpart 5 1.415
## Random###myrandom_classfr 0 0.266
## min.elapsedtime.final max.AUCpROC.fit
## All.X##rcv#glmnet 1.798 0.5867718
## Low.cor.X##rcv#glmnet 1.772 0.5903575
## Max.cor.Y.rcv.1X1###glmnet 0.028 0.5771183
## Max.cor.Y##rcv#rpart 0.015 0.5857237
## Random###myrandom_classfr 0.002 0.4992277
## max.Sens.fit max.Spec.fit max.AUCROCR.fit
## All.X##rcv#glmnet 0.2997573 0.8737864 0.6590272
## Low.cor.X##rcv#glmnet 0.3228155 0.8578994 0.6619830
## Max.cor.Y.rcv.1X1###glmnet 0.3519417 0.8022948 0.6256871
## Max.cor.Y##rcv#rpart 0.4053398 0.7661077 0.6101745
## Random###myrandom_classfr 0.4150485 0.5834069 0.5146734
## opt.prob.threshold.fit max.f.score.fit
## All.X##rcv#glmnet 0.50 0.7333333
## Low.cor.X##rcv#glmnet 0.50 0.7300038
## Max.cor.Y.rcv.1X1###glmnet 0.55 0.6877339
## Max.cor.Y##rcv#rpart 0.50 0.6969089
## Random###myrandom_classfr 0.40 0.7333333
## max.Accuracy.fit max.AccuracyLower.fit
## All.X##rcv#glmnet 0.6055195 0.6102837
## Low.cor.X##rcv#glmnet 0.6050093 0.6108001
## Max.cor.Y.rcv.1X1###glmnet 0.6162494 0.5942872
## Max.cor.Y##rcv#rpart 0.6104535 0.5922249
## Random###myrandom_classfr 0.5789474 0.5567125
## max.AccuracyUpper.fit max.Kappa.fit
## All.X##rcv#glmnet 0.6534996 0.1238626
## Low.cor.X##rcv#glmnet 0.6540036 0.1286240
## Max.cor.Y.rcv.1X1###glmnet 0.6378625 0.1943425
## Max.cor.Y##rcv#rpart 0.6358431 0.1771990
## Random###myrandom_classfr 0.6009453 0.0000000
## max.AUCpROC.OOB max.Sens.OOB max.Spec.OOB
## All.X##rcv#glmnet 0.5067173 0.2009346 0.8125000
## Low.cor.X##rcv#glmnet 0.5091186 0.2196262 0.7986111
## Max.cor.Y.rcv.1X1###glmnet 0.5338785 0.3177570 0.7500000
## Max.cor.Y##rcv#rpart 0.5334729 0.3551402 0.7118056
## Random###myrandom_classfr 0.4990752 0.4252336 0.5729167
## max.AUCROCR.OOB opt.prob.threshold.OOB
## All.X##rcv#glmnet 0.5801856 0.55
## Low.cor.X##rcv#glmnet 0.5816378 0.45
## Max.cor.Y.rcv.1X1###glmnet 0.5592306 0.40
## Max.cor.Y##rcv#rpart 0.5325318 0.40
## Random###myrandom_classfr 0.5181075 0.40
## max.f.score.OOB max.Accuracy.OOB
## All.X##rcv#glmnet 0.6477462 0.5796813
## Low.cor.X##rcv#glmnet 0.7213542 0.5737052
## Max.cor.Y.rcv.1X1###glmnet 0.7291139 0.5737052
## Max.cor.Y##rcv#rpart 0.7291139 0.5737052
## Random###myrandom_classfr 0.7291139 0.5737052
## max.AccuracyLower.OOB max.AccuracyUpper.OOB
## All.X##rcv#glmnet 0.5351418 0.6232769
## Low.cor.X##rcv#glmnet 0.5291204 0.6174170
## Max.cor.Y.rcv.1X1###glmnet 0.5291204 0.6174170
## Max.cor.Y##rcv#rpart 0.5291204 0.6174170
## Random###myrandom_classfr 0.5291204 0.6174170
## max.Kappa.OOB max.AccuracySD.fit
## All.X##rcv#glmnet 0.12865863 0.01174320
## Low.cor.X##rcv#glmnet 0.01492811 0.01148221
## Max.cor.Y.rcv.1X1###glmnet 0.00000000 NA
## Max.cor.Y##rcv#rpart 0.00000000 0.01616114
## Random###myrandom_classfr 0.00000000 NA
## max.KappaSD.fit
## All.X##rcv#glmnet 0.02938213
## Low.cor.X##rcv#glmnet 0.02835557
## Max.cor.Y.rcv.1X1###glmnet NA
## Max.cor.Y##rcv#rpart 0.02629543
## Random###myrandom_classfr NA## min.elapsedtime.everything
## Random###myrandom_classfr 0.266
## MFO###myMFO_classfr 0.473
## Max.cor.Y.rcv.1X1###glmnet 0.721
## Max.cor.Y##rcv#rpart 1.415
## Low.cor.X##rcv#glmnet 15.497
## All.X##rcv#glmnet 15.750## label step_major step_minor label_minor bgn end
## 4 fit.models_1_preProc 1 3 preProc 202.254 203.243
## 5 fit.models_1_end 1 4 teardown 203.244 NA
## elapsed
## 4 0.989
## 5 NA## label step_major step_minor label_minor bgn end elapsed
## 15 fit.models 7 1 1 171.205 203.253 32.048
## 16 fit.models 7 2 2 203.254 NA NA```{r fit.models_2, cache=FALSE, fig.height=10, fig.width=15, eval=myevlChunk(glbChunks, glbOut$pfx)}
## label step_major step_minor label_minor bgn end elapsed
## 1 fit.models_2_bgn 1 0 setup 204.42 NA NA## Warning: max.AccuracyUpper.fit already exists in glb_models_df## [1] "var:max.KappaSD.fit"## Warning: Removed 3 rows containing missing values (geom_errorbar).## quartz_off_screen
## 2## Warning: Removed 3 rows containing missing values (geom_errorbar).
## id max.Accuracy.OOB max.AUCROCR.OOB
## 6 All.X##rcv#glmnet 0.5796813 0.5801856
## 5 Low.cor.X##rcv#glmnet 0.5737052 0.5816378
## 3 Max.cor.Y.rcv.1X1###glmnet 0.5737052 0.5592306
## 4 Max.cor.Y##rcv#rpart 0.5737052 0.5325318
## 2 Random###myrandom_classfr 0.5737052 0.5181075
## 1 MFO###myMFO_classfr 0.5737052 0.5000000
## max.AUCpROC.OOB min.elapsedtime.everything max.Accuracy.fit
## 6 0.5067173 15.750 0.6055195
## 5 0.5091186 15.497 0.6050093
## 3 0.5338785 0.721 0.6162494
## 4 0.5334729 1.415 0.6104535
## 2 0.4990752 0.266 0.5789474
## 1 0.5000000 0.473 0.5789474
## opt.prob.threshold.fit opt.prob.threshold.OOB
## 6 0.50 0.55
## 5 0.50 0.45
## 3 0.55 0.40
## 4 0.50 0.40
## 2 0.40 0.40
## 1 0.40 0.40## [1] "Metrics used for model selection:"## ~-max.Accuracy.OOB - max.AUCROCR.OOB - max.AUCpROC.OOB + min.elapsedtime.everything -
## max.Accuracy.fit - opt.prob.threshold.OOB
## <environment: 0x7fbe4e7a9f88>## [1] "Best model id: All.X##rcv#glmnet"## [1] "User specified selection: All.X##rcv#glmnet"## glmnet
##
## 1957 samples
## 108 predictor
## 2 classes: 'D', 'R'
##
## No pre-processing
## Resampling: Cross-Validated (3 fold, repeated 3 times)
## Summary of sample sizes: 1305, 1305, 1304, 1304, 1305, 1305, ...
## Resampling results across tuning parameters:
##
## alpha lambda Accuracy Kappa
## 0.100 0.03568184 0.5845620 0.11772319
## 0.100 0.05000000 0.5894996 0.12266322
## 0.100 0.06367626 0.5929103 0.12598392
## 0.100 0.07000000 0.5961471 0.13104131
## 0.100 0.09167068 0.5978500 0.12744153
## 0.325 0.03568184 0.5995549 0.13220824
## 0.325 0.05000000 0.6046682 0.13180726
## 0.325 0.06367626 0.6055195 0.12386264
## 0.325 0.07000000 0.6017716 0.11086277
## 0.325 0.09167068 0.5934247 0.07302233
## 0.550 0.03568184 0.6050093 0.12862401
## 0.550 0.05000000 0.5990460 0.09952083
## 0.550 0.06367626 0.5872918 0.04483622
## 0.550 0.07000000 0.5816741 0.01389986
## 0.550 0.09167068 0.5789474 0.00000000
## 0.775 0.03568184 0.5990463 0.10159305
## 0.775 0.05000000 0.5815036 0.01367876
## 0.775 0.06367626 0.5789474 0.00000000
## 0.775 0.07000000 0.5789474 0.00000000
## 0.775 0.09167068 0.5789474 0.00000000
## 1.000 0.03568184 0.5901878 0.05538669
## 1.000 0.05000000 0.5789474 0.00000000
## 1.000 0.06367626 0.5789474 0.00000000
## 1.000 0.07000000 0.5789474 0.00000000
## 1.000 0.09167068 0.5789474 0.00000000
##
## Accuracy was used to select the optimal model using the largest value.
## The final values used for the model were alpha = 0.325 and lambda
## = 0.06367626.## [1] "All.X##rcv#glmnet fit prediction diagnostics:"## [1] "All.X##rcv#glmnet OOB prediction diagnostics:"## All.X..rcv.glmnet.imp imp
## Hhold.fctrPKn 100.000000 100.000000
## Q113181.fctrYes 64.984274 64.984274
## Q115611.fctrYes 52.729697 52.729697
## Q113181.fctrNo 51.264404 51.264404
## Q115611.fctrNo 44.707621 44.707621
## Q98197.fctrNo 40.627886 40.627886
## Q101163.fctrDad 27.773431 27.773431
## Hhold.fctrMKy 25.424438 25.424438
## Q116881.fctrRight 23.579086 23.579086
## Q106272.fctrYes 22.437747 22.437747
## Hhold.fctrPKy 17.918579 17.918579
## Q106997.fctrGr 15.677653 15.677653
## Q110740.fctrPC 11.933368 11.933368
## Q100562.fctrNo 9.122468 9.122468
## Q99480.fctrNo 6.082982 6.082982
## Income.fctr.Q 5.630958 5.630958
## Q119650.fctrGiving 5.596421 5.596421
## Q98869.fctrNo 5.552206 5.552206
## Q115899.fctrCs 5.392219 5.392219
## Q116881.fctrHappy 3.039743 3.039743
## Income.fctr.C 2.839396 2.839396
## Q119650.fctrReceiving 1.557860 1.557860
## .rnorm 0.000000 0.000000
## Edn.fctr.L 0.000000 0.000000
## Edn.fctr.Q 0.000000 0.000000
## Edn.fctr.C 0.000000 0.000000
## Edn.fctr^4 0.000000 0.000000
## Edn.fctr^5 0.000000 0.000000
## Edn.fctr^6 0.000000 0.000000
## Edn.fctr^7 0.000000 0.000000
## Gender.fctrF 0.000000 0.000000
## Gender.fctrM 0.000000 0.000000
## Hhold.fctrMKn 0.000000 0.000000
## Hhold.fctrSKn 0.000000 0.000000
## Hhold.fctrSKy 0.000000 0.000000
## Income.fctr.L 0.000000 0.000000
## Income.fctr^4 0.000000 0.000000
## Income.fctr^5 0.000000 0.000000
## Income.fctr^6 0.000000 0.000000
## Q100010.fctrNo 0.000000 0.000000
## Q100010.fctrYes 0.000000 0.000000
## Q100562.fctrYes 0.000000 0.000000
## Q100680.fctrNo 0.000000 0.000000
## Q100680.fctrYes 0.000000 0.000000
## Q100689.fctrNo 0.000000 0.000000
## Q100689.fctrYes 0.000000 0.000000
## Q101162.fctrOptimist 0.000000 0.000000
## Q101162.fctrPessimist 0.000000 0.000000
## Q101163.fctrMom 0.000000 0.000000
## Q101596.fctrNo 0.000000 0.000000
## Q101596.fctrYes 0.000000 0.000000
## Q102089.fctrOwn 0.000000 0.000000
## Q102089.fctrRent 0.000000 0.000000
## Q102289.fctrNo 0.000000 0.000000
## Q102289.fctrYes 0.000000 0.000000
## Q102674.fctrNo 0.000000 0.000000
## Q102674.fctrYes 0.000000 0.000000
## Q102687.fctrNo 0.000000 0.000000
## Q102687.fctrYes 0.000000 0.000000
## Q102906.fctrNo 0.000000 0.000000
## Q102906.fctrYes 0.000000 0.000000
## Q103293.fctrNo 0.000000 0.000000
## Q103293.fctrYes 0.000000 0.000000
## Q104996.fctrNo 0.000000 0.000000
## Q104996.fctrYes 0.000000 0.000000
## Q105655.fctrNo 0.000000 0.000000
## Q105655.fctrYes 0.000000 0.000000
## Q105840.fctrNo 0.000000 0.000000
## Q105840.fctrYes 0.000000 0.000000
## Q106042.fctrNo 0.000000 0.000000
## Q106042.fctrYes 0.000000 0.000000
## Q106272.fctrNo 0.000000 0.000000
## Q106388.fctrNo 0.000000 0.000000
## Q106388.fctrYes 0.000000 0.000000
## Q106389.fctrNo 0.000000 0.000000
## Q106389.fctrYes 0.000000 0.000000
## Q106993.fctrNo 0.000000 0.000000
## Q106993.fctrYes 0.000000 0.000000
## Q106997.fctrYy 0.000000 0.000000
## Q107491.fctrNo 0.000000 0.000000
## Q107491.fctrYes 0.000000 0.000000
## Q107869.fctrNo 0.000000 0.000000
## Q107869.fctrYes 0.000000 0.000000
## Q108342.fctrIn-person 0.000000 0.000000
## Q108342.fctrOnline 0.000000 0.000000
## Q108343.fctrNo 0.000000 0.000000
## Q108343.fctrYes 0.000000 0.000000
## Q108617.fctrNo 0.000000 0.000000
## Q108617.fctrYes 0.000000 0.000000
## Q108754.fctrNo 0.000000 0.000000
## Q108754.fctrYes 0.000000 0.000000
## Q108855.fctrUmm... 0.000000 0.000000
## Q108855.fctrYes! 0.000000 0.000000
## Q108856.fctrSocialize 0.000000 0.000000
## Q108856.fctrSpace 0.000000 0.000000
## Q108950.fctrCautious 0.000000 0.000000
## Q108950.fctrRisk-friendly 0.000000 0.000000
## Q109367.fctrNo 0.000000 0.000000
## Q109367.fctrYes 0.000000 0.000000
## Q110740.fctrMac 0.000000 0.000000
## Q111220.fctrNo 0.000000 0.000000
## Q111220.fctrYes 0.000000 0.000000
## Q111580.fctrDemanding 0.000000 0.000000
## Q111580.fctrSupportive 0.000000 0.000000
## Q111848.fctrNo 0.000000 0.000000
## Q111848.fctrYes 0.000000 0.000000
## Q112270.fctrNo 0.000000 0.000000
## Q112270.fctrYes 0.000000 0.000000
## Q112478.fctrNo 0.000000 0.000000
## Q112478.fctrYes 0.000000 0.000000
## Q112512.fctrNo 0.000000 0.000000
## Q112512.fctrYes 0.000000 0.000000
## Q113583.fctrTalk 0.000000 0.000000
## Q113583.fctrTunes 0.000000 0.000000
## Q113584.fctrPeople 0.000000 0.000000
## Q113584.fctrTechnology 0.000000 0.000000
## Q113992.fctrNo 0.000000 0.000000
## Q113992.fctrYes 0.000000 0.000000
## Q114152.fctrNo 0.000000 0.000000
## Q114152.fctrYes 0.000000 0.000000
## Q114386.fctrMysterious 0.000000 0.000000
## Q114386.fctrTMI 0.000000 0.000000
## Q114517.fctrNo 0.000000 0.000000
## Q114517.fctrYes 0.000000 0.000000
## Q114748.fctrNo 0.000000 0.000000
## Q114748.fctrYes 0.000000 0.000000
## Q114961.fctrNo 0.000000 0.000000
## Q114961.fctrYes 0.000000 0.000000
## Q115195.fctrNo 0.000000 0.000000
## Q115195.fctrYes 0.000000 0.000000
## Q115390.fctrNo 0.000000 0.000000
## Q115390.fctrYes 0.000000 0.000000
## Q115602.fctrNo 0.000000 0.000000
## Q115602.fctrYes 0.000000 0.000000
## Q115610.fctrNo 0.000000 0.000000
## Q115610.fctrYes 0.000000 0.000000
## Q115777.fctrEnd 0.000000 0.000000
## Q115777.fctrStart 0.000000 0.000000
## Q115899.fctrMe 0.000000 0.000000
## Q116197.fctrA.M. 0.000000 0.000000
## Q116197.fctrP.M. 0.000000 0.000000
## Q116441.fctrNo 0.000000 0.000000
## Q116441.fctrYes 0.000000 0.000000
## Q116448.fctrNo 0.000000 0.000000
## Q116448.fctrYes 0.000000 0.000000
## Q116601.fctrNo 0.000000 0.000000
## Q116601.fctrYes 0.000000 0.000000
## Q116797.fctrNo 0.000000 0.000000
## Q116797.fctrYes 0.000000 0.000000
## Q116953.fctrNo 0.000000 0.000000
## Q116953.fctrYes 0.000000 0.000000
## Q117186.fctrCool headed 0.000000 0.000000
## Q117186.fctrHot headed 0.000000 0.000000
## Q117193.fctrOdd hours 0.000000 0.000000
## Q117193.fctrStandard hours 0.000000 0.000000
## Q118117.fctrNo 0.000000 0.000000
## Q118117.fctrYes 0.000000 0.000000
## Q118232.fctrId 0.000000 0.000000
## Q118232.fctrPr 0.000000 0.000000
## Q118233.fctrNo 0.000000 0.000000
## Q118233.fctrYes 0.000000 0.000000
## Q118237.fctrNo 0.000000 0.000000
## Q118237.fctrYes 0.000000 0.000000
## Q118892.fctrNo 0.000000 0.000000
## Q118892.fctrYes 0.000000 0.000000
## Q119334.fctrNo 0.000000 0.000000
## Q119334.fctrYes 0.000000 0.000000
## Q119851.fctrNo 0.000000 0.000000
## Q119851.fctrYes 0.000000 0.000000
## Q120012.fctrNo 0.000000 0.000000
## Q120012.fctrYes 0.000000 0.000000
## Q120014.fctrNo 0.000000 0.000000
## Q120014.fctrYes 0.000000 0.000000
## Q120194.fctrStudy first 0.000000 0.000000
## Q120194.fctrTry first 0.000000 0.000000
## Q120379.fctrNo 0.000000 0.000000
## Q120379.fctrYes 0.000000 0.000000
## Q120472.fctrArt 0.000000 0.000000
## Q120472.fctrScience 0.000000 0.000000
## Q120650.fctrNo 0.000000 0.000000
## Q120650.fctrYes 0.000000 0.000000
## Q120978.fctrNo 0.000000 0.000000
## Q120978.fctrYes 0.000000 0.000000
## Q121011.fctrNo 0.000000 0.000000
## Q121011.fctrYes 0.000000 0.000000
## Q121699.fctrNo 0.000000 0.000000
## Q121699.fctrYes 0.000000 0.000000
## Q121700.fctrNo 0.000000 0.000000
## Q121700.fctrYes 0.000000 0.000000
## Q122120.fctrNo 0.000000 0.000000
## Q122120.fctrYes 0.000000 0.000000
## Q122769.fctrNo 0.000000 0.000000
## Q122769.fctrYes 0.000000 0.000000
## Q122770.fctrNo 0.000000 0.000000
## Q122770.fctrYes 0.000000 0.000000
## Q122771.fctrPc 0.000000 0.000000
## Q122771.fctrPt 0.000000 0.000000
## Q123464.fctrNo 0.000000 0.000000
## Q123464.fctrYes 0.000000 0.000000
## Q123621.fctrNo 0.000000 0.000000
## Q123621.fctrYes 0.000000 0.000000
## Q124122.fctrNo 0.000000 0.000000
## Q124122.fctrYes 0.000000 0.000000
## Q124742.fctrNo 0.000000 0.000000
## Q124742.fctrYes 0.000000 0.000000
## Q96024.fctrNo 0.000000 0.000000
## Q96024.fctrYes 0.000000 0.000000
## Q98059.fctrOnly-child 0.000000 0.000000
## Q98059.fctrYes 0.000000 0.000000
## Q98078.fctrNo 0.000000 0.000000
## Q98078.fctrYes 0.000000 0.000000
## Q98197.fctrYes 0.000000 0.000000
## Q98578.fctrNo 0.000000 0.000000
## Q98578.fctrYes 0.000000 0.000000
## Q98869.fctrYes 0.000000 0.000000
## Q99480.fctrYes 0.000000 0.000000
## Q99581.fctrNo 0.000000 0.000000
## Q99581.fctrYes 0.000000 0.000000
## Q99716.fctrNo 0.000000 0.000000
## Q99716.fctrYes 0.000000 0.000000
## Q99982.fctrCheck! 0.000000 0.000000
## Q99982.fctrNope 0.000000 0.000000
## YOB.Age.fctr.L 0.000000 0.000000
## YOB.Age.fctr.Q 0.000000 0.000000
## YOB.Age.fctr.C 0.000000 0.000000
## YOB.Age.fctr^4 0.000000 0.000000
## YOB.Age.fctr^5 0.000000 0.000000
## YOB.Age.fctr^6 0.000000 0.000000
## YOB.Age.fctr^7 0.000000 0.000000
## YOB.Age.fctr^8 0.000000 0.000000
## Hhold.fctrN:.clusterid.fctr2 0.000000 0.000000
## Hhold.fctrMKn:.clusterid.fctr2 0.000000 0.000000
## Hhold.fctrMKy:.clusterid.fctr2 0.000000 0.000000
## Hhold.fctrPKn:.clusterid.fctr2 0.000000 0.000000
## Hhold.fctrPKy:.clusterid.fctr2 0.000000 0.000000
## Hhold.fctrSKn:.clusterid.fctr2 0.000000 0.000000
## Hhold.fctrSKy:.clusterid.fctr2 0.000000 0.000000
## Hhold.fctrN:.clusterid.fctr3 0.000000 0.000000
## Hhold.fctrMKn:.clusterid.fctr3 0.000000 0.000000
## Hhold.fctrMKy:.clusterid.fctr3 0.000000 0.000000
## Hhold.fctrPKn:.clusterid.fctr3 0.000000 0.000000
## Hhold.fctrPKy:.clusterid.fctr3 0.000000 0.000000
## Hhold.fctrSKn:.clusterid.fctr3 0.000000 0.000000
## Hhold.fctrSKy:.clusterid.fctr3 0.000000 0.000000
## Hhold.fctrN:.clusterid.fctr4 0.000000 0.000000
## Hhold.fctrMKn:.clusterid.fctr4 0.000000 0.000000
## Hhold.fctrMKy:.clusterid.fctr4 0.000000 0.000000
## Hhold.fctrPKn:.clusterid.fctr4 0.000000 0.000000
## Hhold.fctrPKy:.clusterid.fctr4 0.000000 0.000000
## Hhold.fctrSKn:.clusterid.fctr4 0.000000 0.000000
## Hhold.fctrSKy:.clusterid.fctr4 0.000000 0.000000
## YOB.Age.fctrNA:YOB.Age.dff 0.000000 0.000000
## YOB.Age.fctr(15,20]:YOB.Age.dff 0.000000 0.000000
## YOB.Age.fctr(20,25]:YOB.Age.dff 0.000000 0.000000
## YOB.Age.fctr(25,30]:YOB.Age.dff 0.000000 0.000000
## YOB.Age.fctr(30,35]:YOB.Age.dff 0.000000 0.000000
## YOB.Age.fctr(35,40]:YOB.Age.dff 0.000000 0.000000
## YOB.Age.fctr(40,50]:YOB.Age.dff 0.000000 0.000000
## YOB.Age.fctr(50,65]:YOB.Age.dff 0.000000 0.000000
## YOB.Age.fctr(65,90]:YOB.Age.dff 0.000000 0.000000## Warning in glb_analytics_diag_plots(obs_df = glbObsOOB, mdl_id =
## glbMdlSelId, : Limiting important feature scatter plots to 5 out of 108
## [1] "Min/Max Boundaries: "
## [1] "Inaccurate: "
## USER_ID Party.fctr Party.fctr.All.X..rcv.glmnet.prob
## 1 470 R 0.4178772
## 2 2565 R 0.4433796
## 3 1275 R 0.4443487
## 4 574 R 0.4477939
## 5 381 R 0.4483704
## 6 3577 R 0.4521859
## Party.fctr.All.X..rcv.glmnet Party.fctr.All.X..rcv.glmnet.err
## 1 D TRUE
## 2 D TRUE
## 3 D TRUE
## 4 D TRUE
## 5 D TRUE
## 6 D TRUE
## Party.fctr.All.X..rcv.glmnet.err.abs Party.fctr.All.X..rcv.glmnet.is.acc
## 1 0.5821228 FALSE
## 2 0.5566204 FALSE
## 3 0.5556513 FALSE
## 4 0.5522061 FALSE
## 5 0.5516296 FALSE
## 6 0.5478141 FALSE
## Party.fctr.All.X..rcv.glmnet.accurate Party.fctr.All.X..rcv.glmnet.error
## 1 FALSE -0.13212279
## 2 FALSE -0.10662037
## 3 FALSE -0.10565126
## 4 FALSE -0.10220608
## 5 FALSE -0.10162960
## 6 FALSE -0.09781408
## USER_ID Party.fctr Party.fctr.All.X..rcv.glmnet.prob
## 24 2557 R 0.4751736
## 41 4602 R 0.4848311
## 47 3566 R 0.4909901
## 51 4337 R 0.4969843
## 131 1657 D 0.5892389
## 166 5783 D 0.6244881
## Party.fctr.All.X..rcv.glmnet Party.fctr.All.X..rcv.glmnet.err
## 24 D TRUE
## 41 D TRUE
## 47 D TRUE
## 51 D TRUE
## 131 R TRUE
## 166 R TRUE
## Party.fctr.All.X..rcv.glmnet.err.abs
## 24 0.5248264
## 41 0.5151689
## 47 0.5090099
## 51 0.5030157
## 131 0.5892389
## 166 0.6244881
## Party.fctr.All.X..rcv.glmnet.is.acc
## 24 FALSE
## 41 FALSE
## 47 FALSE
## 51 FALSE
## 131 FALSE
## 166 FALSE
## Party.fctr.All.X..rcv.glmnet.accurate
## 24 FALSE
## 41 FALSE
## 47 FALSE
## 51 FALSE
## 131 FALSE
## 166 FALSE
## Party.fctr.All.X..rcv.glmnet.error
## 24 -0.07482638
## 41 -0.06516889
## 47 -0.05900991
## 51 -0.05301572
## 131 0.03923887
## 166 0.07448809
## USER_ID Party.fctr Party.fctr.All.X..rcv.glmnet.prob
## 206 483 D 0.7087168
## 207 1263 D 0.7105345
## 208 613 D 0.7141901
## 209 3512 D 0.7178165
## 210 3978 D 0.7238014
## 211 4956 D 0.7303139
## Party.fctr.All.X..rcv.glmnet Party.fctr.All.X..rcv.glmnet.err
## 206 R TRUE
## 207 R TRUE
## 208 R TRUE
## 209 R TRUE
## 210 R TRUE
## 211 R TRUE
## Party.fctr.All.X..rcv.glmnet.err.abs
## 206 0.7087168
## 207 0.7105345
## 208 0.7141901
## 209 0.7178165
## 210 0.7238014
## 211 0.7303139
## Party.fctr.All.X..rcv.glmnet.is.acc
## 206 FALSE
## 207 FALSE
## 208 FALSE
## 209 FALSE
## 210 FALSE
## 211 FALSE
## Party.fctr.All.X..rcv.glmnet.accurate
## 206 FALSE
## 207 FALSE
## 208 FALSE
## 209 FALSE
## 210 FALSE
## 211 FALSE
## Party.fctr.All.X..rcv.glmnet.error
## 206 0.1587168
## 207 0.1605345
## 208 0.1641901
## 209 0.1678165
## 210 0.1738014
## 211 0.1803139
## Hhold.fctr .n.OOB .n.Fit .n.Tst .freqRatio.Fit .freqRatio.OOB
## PKy PKy 6 14 6 0.007153807 0.01195219
## PKn PKn 13 50 15 0.025549310 0.02589641
## SKy SKy 23 61 27 0.031170158 0.04581673
## N N 28 116 33 0.059274400 0.05577689
## MKn MKn 75 226 94 0.115482882 0.14940239
## SKn SKn 201 810 252 0.413898825 0.40039841
## MKy MKy 156 680 195 0.347470618 0.31075697
## .freqRatio.Tst err.abs.fit.sum err.abs.fit.mean .n.fit err.abs.OOB.sum
## PKy 0.009646302 7.086145 0.5061532 14 3.238914
## PKn 0.024115756 24.399436 0.4879887 50 6.726635
## SKy 0.043408360 28.898436 0.4737449 61 11.815230
## N 0.053054662 54.104346 0.4664168 116 13.604103
## MKn 0.151125402 104.765360 0.4635635 226 35.796619
## SKn 0.405144695 386.381033 0.4770136 810 95.720498
## MKy 0.313504823 308.646219 0.4538915 680 72.981800
## err.abs.OOB.mean
## PKy 0.5398191
## PKn 0.5174334
## SKy 0.5137057
## N 0.4858608
## MKn 0.4772882
## SKn 0.4762214
## MKy 0.4678321
## .n.OOB .n.Fit .n.Tst .freqRatio.Fit
## 502.000000 1957.000000 622.000000 1.000000
## .freqRatio.OOB .freqRatio.Tst err.abs.fit.sum err.abs.fit.mean
## 1.000000 1.000000 914.280975 3.328772
## .n.fit err.abs.OOB.sum err.abs.OOB.mean
## 1957.000000 239.883799 3.478161## label step_major step_minor label_minor bgn end elapsed
## 1 fit.models_2_bgn 1 0 teardown 210.854 NA NA## label step_major step_minor label_minor bgn end elapsed
## 16 fit.models 7 2 2 203.254 210.864 7.61
## 17 fit.models 7 3 3 210.865 NA NA# if (sum(is.na(glbObsAll$D.P.http)) > 0)
# stop("fit.models_3: Why is this happening ?")
#stop(here"); glb2Sav()
sync_glb_obs_df <- function() {
# Merge or cbind ?
for (col in setdiff(names(glbObsFit), names(glbObsTrn)))
glbObsTrn[glbObsTrn$.lcn == "Fit", col] <<- glbObsFit[, col]
for (col in setdiff(names(glbObsFit), names(glbObsAll)))
glbObsAll[glbObsAll$.lcn == "Fit", col] <<- glbObsFit[, col]
if (all(is.na(glbObsNew[, glb_rsp_var])))
for (col in setdiff(names(glbObsOOB), names(glbObsTrn)))
glbObsTrn[glbObsTrn$.lcn == "OOB", col] <<- glbObsOOB[, col]
for (col in setdiff(names(glbObsOOB), names(glbObsAll)))
glbObsAll[glbObsAll$.lcn == "OOB", col] <<- glbObsOOB[, col]
}
sync_glb_obs_df()
print(setdiff(names(glbObsNew), names(glbObsAll)))## character(0)replay.petrisim(pn = glb_analytics_pn,
replay.trans = (glb_analytics_avl_objs <- c(glb_analytics_avl_objs,
"model.selected")), flip_coord = TRUE)## time trans "bgn " "fit.data.training.all " "predict.data.new " "end "
## 0.0000 multiple enabled transitions: data.training.all data.new model.selected firing: data.training.all
## 1.0000 1 2 1 0 0
## 1.0000 multiple enabled transitions: data.training.all data.new model.selected model.final data.training.all.prediction firing: data.new
## 2.0000 2 1 1 1 0
## 2.0000 multiple enabled transitions: data.training.all data.new model.selected model.final data.training.all.prediction data.new.prediction firing: model.selected
## 3.0000 3 0 2 1 0
glb_chunks_df <- myadd_chunk(glb_chunks_df, "fit.data.training", major.inc = TRUE)## label step_major step_minor label_minor bgn end
## 17 fit.models 7 3 3 210.865 213.91
## 18 fit.data.training 8 0 0 213.910 NA
## elapsed
## 17 3.045
## 18 NAStep 8.0: fit data training
#load(paste0(glb_inp_pfx, "dsk.RData"))
if (!is.null(glbMdlFinId) && (glbMdlFinId %in% names(glb_models_lst))) {
warning("Final model same as user selected model")
glb_fin_mdl <- glb_models_lst[[glbMdlFinId]]
} else
# if (nrow(glbObsFit) + length(glbObsFitOutliers) == nrow(glbObsTrn))
if (!all(is.na(glbObsNew[, glb_rsp_var]))) {
warning("Final model same as glbMdlSelId")
glbMdlFinId <- paste0("Final.", glbMdlSelId)
glb_fin_mdl <- glb_sel_mdl
glb_models_lst[[glbMdlFinId]] <- glb_fin_mdl
mdlDf <- glb_models_df[glb_models_df$id == glbMdlSelId, ]
mdlDf$id <- glbMdlFinId
glb_models_df <- rbind(glb_models_df, mdlDf)
} else {
if (myparseMdlId(glbMdlSelId)$family == "RFE.X") {
indepVar <- mygetIndepVar(glb_feats_df)
trnRFEResults <-
myrun_rfe(glbObsTrn, indepVar, glbRFESizes[["Final"]])
if (!isTRUE(all.equal(sort(predictors(trnRFEResults)),
sort(predictors(glbRFEResults))))) {
print("Diffs predictors(trnRFEResults) vs. predictors(glbRFEResults):")
print(setdiff(predictors(trnRFEResults), predictors(glbRFEResults)))
print("Diffs predictors(glbRFEResults) vs. predictors(trnRFEResults):")
print(setdiff(predictors(glbRFEResults), predictors(trnRFEResults)))
}
}
if (grepl("Ensemble", glbMdlSelId)) {
# Find which models are relevant
mdlimp_df <- subset(myget_feats_importance(glb_sel_mdl), imp > 5)
mdlIndepVar <- row.names(mdlimp_df)
if (glb_is_classification)
mdlIdVcr <- glbMdlEnsemble[sapply(glbMdlEnsemble, function(thsMdlId)
mygetPredictIds(glb_rsp_var, thsMdlId)$prob %in% mdlIndepVar)] else
mdlIdVcr <- glbMdlEnsemble[sapply(glbMdlEnsemble, function(thsMdlId)
mygetPredictIds(glb_rsp_var, thsMdlId)$value %in% mdlIndepVar)]
# Fit selected models on glbObsTrn
for (mdl_id in mdlIdVcr) {
mdl_id_components <- myparseMdlId(mdl_id)
mdlIdPfx <- mdl_id_components$family
# if (grepl("RFE\\.X\\.", mdlIdPfx))
# mdlIndepVars <- myadjustInteractionFeats(glb_feats_df, myextract_actual_feats(
# predictors(trnRFEResults))) else
# mdlIndepVars <- trim(unlist(
# strsplit(glb_models_df[glb_models_df$id == mdl_id, "feats"], "[,]")))
thsIndepVar <- unlist(
strsplit(glb_models_df[glb_models_df$id == mdl_id, "feats"], "[,]"))
thsSpc <- myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = paste0("Final.", mdlIdPfx),
type = glb_model_type, tune.df = glbMdlTuneParams,
trainControl.method = mdl_id_components$resample,
trainControl.number = glb_rcv_n_folds,
trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = mdl_id_components$alg,
train.preProcess = mdl_id_components$preProcess))
ret_lst <- myfit_mdl(mdl_specs_lst = thsSpc,
indepVar = thsIndepVar,
rsp_var = glb_rsp_var,
fit_df = glbObsTrn, OOB_df = NULL)
glbObsTrn <- glb_get_predictions(df = glbObsTrn,
mdl_id = thsSpc$id,
rsp_var = glb_rsp_var,
prob_threshold_def =
subset(glb_models_df, id == mdl_id)$opt.prob.threshold.OOB)
glbObsNew <- glb_get_predictions(df = glbObsNew,
mdl_id = thsSpc$id,
rsp_var = glb_rsp_var,
prob_threshold_def =
subset(glb_models_df, id == mdl_id)$opt.prob.threshold.OOB)
}
}
# "Final" model
if ((model_method <- glb_sel_mdl$method) == "custom")
# get actual method from the mdl_id
model_method <- tail(unlist(strsplit(glbMdlSelId, "[.]")), 1)
if (grepl("Ensemble", glbMdlSelId)) {
# Find which models are relevant
mdlimp_df <- subset(myget_feats_importance(glb_sel_mdl), imp > 5)
mdlIndepVar <- row.names(mdlimp_df)
if (glb_is_classification)
mdlIdVcr <- glbMdlEnsemble[sapply(glbMdlEnsemble, function(thsMdlId)
mygetPredictIds(glb_rsp_var, thsMdlId)$prob %in% mdlIndepVar)] else
mdlIdVcr <- glbMdlEnsemble[sapply(glbMdlEnsemble, function(thsMdlId)
mygetPredictIds(glb_rsp_var, thsMdlId)$value %in% mdlIndepVar)]
mdlIdVcr <- paste("Final", mdlIdVcr, sep = ".")
mdlIndepVar <- gsub(glb_rsp_var, paste0(glb_rsp_var, ".Final"), mdlIndepVar, fixed = TRUE)
# if (glb_is_classification && glb_is_binomial)
# indepVar <- gsub("(.*)\\.(.*)\\.prob", "\\1\\.Train\\.\\2\\.prob",
# row.names(mdlimp_df)) else
# indepVar <- gsub("(.*)\\.(.*)", "\\1\\.Train\\.\\2",
# row.names(mdlimp_df))
} else
if (grepl("RFE.X", glbMdlSelId, fixed = TRUE)) {
# indepVar <- myextract_actual_feats(predictors(trnRFEResults))
mdlIndepVar <- myextract_actual_feats(predictors(glbRFEResults))
} else mdlIndepVar <-
trim(unlist(strsplit(glb_models_df[glb_models_df$id ==
glbMdlSelId
, "feats"], "[,]")))
# if (!is.null(glbMdlPreprocMethods) &&
# ((match_pos <- regexpr(gsub(".", "\\.",
# paste(glbMdlPreprocMethods, collapse = "|"),
# fixed = TRUE), glbMdlSelId)) != -1))
# ths_preProcess <- str_sub(glbMdlSelId, match_pos,
# match_pos + attr(match_pos, "match.length") - 1) else
# ths_preProcess <- NULL
# mdl_id_pfx <- ifelse(grepl("Ensemble", glbMdlSelId),
# "Final.Ensemble", "Final")
thsMdlId <- paste0("Final.", glbMdlSelId)
thsMdlIdComponents <- myparseMdlId(thsMdlId)
# mdl_id_pfx <- paste("Final", myparseMdlId(glbMdlSelId)$family, sep = ".")
mdl_id_pfx <- thsMdlIdComponents$family
trnobs_df <- glbObsTrn
if (!is.null(glbObsTrnOutliers[[mdl_id_pfx]])) {
trnobs_df <- glbObsTrn[!(glbObsTrn[, glbFeatsId] %in% glbObsTrnOutliers[[mdl_id_pfx]]), ]
print(sprintf("Outliers removed: %d", nrow(glbObsTrn) - nrow(trnobs_df)))
print(setdiff(glbObsTrn[, glbFeatsId], trnobs_df[, glbFeatsId]))
}
# Force fitting of Final.glm to identify outliers
# method_vctr <- unique(c(myparseMdlId(glbMdlSelId)$alg, glbMdlFamilies[["Final"]]))
thsSpc <- myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = mdl_id_pfx,
type = glb_model_type, tune.df = glbMdlTuneParams,
trainControl.method = thsMdlIdComponents$resample,
trainControl.number = glb_rcv_n_folds,
trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = thsMdlIdComponents$alg,
train.preProcess = thsMdlIdComponents$preProcess))
glbMdlFinId <- thsSpc$id
if (!(grepl("Ensemble", glbMdlSelId)))
ret_lst <- myfit_mdl(mdl_specs_lst = thsSpc,
indepVar = mdlIndepVar,
rsp_var = glb_rsp_var,
fit_df = glbObsTrn, OOB_df = NULL) else {
# Final model same as selected model except for the model features
tmp_models_df <- glb_models_df[glb_models_df$id == glbMdlSelId, ]
tmp_models_df$id <- paste0("Final.", tmp_models_df$id)
row.names(tmp_models_df) <- tmp_models_df$id
tmp_models_df$feats <- gsub(glb_rsp_var, paste0(glb_rsp_var, ".Final"),
tmp_models_df$feats, fixed = TRUE)
glb_models_df <- rbind(glb_models_df, tmp_models_df)
tmp_fin_mdl <- glb_sel_mdl
# tmp_fin_mdl$coefnames <- gsub(glb_rsp_var, paste0(glb_rsp_var, ".Final"),
# tmp_fin_mdl$coefnames, fixed = TRUE)
# dimnames(tmp_fin_mdl$finalModel$beta)[[1]] <-
# gsub(glb_rsp_var, paste0(glb_rsp_var, ".Final"),
# dimnames(tmp_fin_mdl$finalModel$beta)[[1]], fixed = TRUE)
# tmp_fin_mdl$finalModel$xNames <-
# gsub(glb_rsp_var, paste0(glb_rsp_var, ".Final"),
# tmp_fin_mdl$finalModel$xNames, fixed = TRUE)
#
# thsAts <- attributes(tmp_fin_mdl$terms)
# # thsAts$variables <- class == "call" & objects / symbols are stored as a formula
# thsAts$term.labels <-
# gsub(glb_rsp_var, paste0(glb_rsp_var, ".Final"),
# thsAts$term.labels, fixed = TRUE)
# attributes(tmp_fin_mdl$terms) <- thsAts
#
glb_models_lst[[glbMdlFinId]] <- tmp_fin_mdl
}
glb_fin_mdl <- glb_models_lst[[glbMdlFinId]]
}## [1] "myfit_mdl: enter: 0.000000 secs"
## [1] "myfit_mdl: fitting model: Final.All.X##rcv#glmnet"
## [1] " indepVar: Q115611.fctr,Q113181.fctr,Q98197.fctr,Q116881.fctr,Q108855.fctr,Q106272.fctr,Q122771.fctr,Q123621.fctr,Q106388.fctr,Q110740.fctr,Q122769.fctr,Q120472.fctr,Q101596.fctr,Q119334.fctr,Q114152.fctr,Q98869.fctr,Q115899.fctr,Q116797.fctr,Q118232.fctr,Gender.fctr,Q105655.fctr,Q99480.fctr,Q123464.fctr,Q120650.fctr,Q122120.fctr,Q107869.fctr,Q120014.fctr,Q102289.fctr,Income.fctr,Q122770.fctr,Q111580.fctr,Q116601.fctr,Q117186.fctr,Q106993.fctr,Q112270.fctr,Q101162.fctr,Q108856.fctr,Q117193.fctr,Q116441.fctr,Q119851.fctr,Q111848.fctr,Q98578.fctr,Q118892.fctr,Q114386.fctr,Q120978.fctr,Q112512.fctr,Q102674.fctr,Q96024.fctr,Q108950.fctr,Q115610.fctr,YOB.Age.fctr,Q112478.fctr,Q116197.fctr,Q124742.fctr,Q106389.fctr,Edn.fctr,Q118117.fctr,Q100562.fctr,Q107491.fctr,Q116448.fctr,Q108754.fctr,Q116953.fctr,Q115602.fctr,Q118233.fctr,Q120012.fctr,Q118237.fctr,Q99581.fctr,.rnorm,Q120194.fctr,Q115777.fctr,Q106997.fctr,Q100680.fctr,Q113584.fctr,Q108343.fctr,Q121700.fctr,Q105840.fctr,Q120379.fctr,Q103293.fctr,Q124122.fctr,Q109367.fctr,Q113992.fctr,Q121699.fctr,Q121011.fctr,Q114748.fctr,Q106042.fctr,Q111220.fctr,Q114517.fctr,Q102687.fctr,Q102906.fctr,Q98078.fctr,Q115390.fctr,Q102089.fctr,Q100010.fctr,Q99982.fctr,Q113583.fctr,Q108342.fctr,Q104996.fctr,Q119650.fctr,Q100689.fctr,Q108617.fctr,Q115195.fctr,Q99716.fctr,Q101163.fctr,Q98059.fctr,Q114961.fctr,Hhold.fctr,Hhold.fctr:.clusterid.fctr,YOB.Age.fctr:YOB.Age.dff"
## [1] "myfit_mdl: setup complete: 0.677000 secs"
## Aggregating results
## Selecting tuning parameters
## Fitting alpha = 0.55, lambda = 0.0299 on full training set
## [1] "myfit_mdl: train complete: 19.109000 secs"
## Length Class Mode
## a0 79 -none- numeric
## beta 20540 dgCMatrix S4
## df 79 -none- numeric
## dim 2 -none- numeric
## lambda 79 -none- numeric
## dev.ratio 79 -none- numeric
## nulldev 1 -none- numeric
## npasses 1 -none- numeric
## jerr 1 -none- numeric
## offset 1 -none- logical
## classnames 2 -none- character
## call 5 -none- call
## nobs 1 -none- numeric
## lambdaOpt 1 -none- numeric
## xNames 260 -none- character
## problemType 1 -none- character
## tuneValue 2 data.frame list
## obsLevels 2 -none- character
## [1] "min lambda > lambdaOpt:"
## (Intercept) Hhold.fctrMKy
## 0.239007070 0.033507266
## Hhold.fctrPKn Hhold.fctrPKy
## -0.227686861 -0.032591893
## Income.fctr.Q Q100562.fctrNo
## 0.039333160 -0.018180749
## Q101163.fctrDad Q106272.fctrNo
## 0.125067724 -0.034909617
## Q106997.fctrGr Q108855.fctrYes!
## 0.059926842 0.037896957
## Q110740.fctrPC Q113181.fctrNo
## 0.071996630 -0.176627116
## Q113181.fctrYes Q115611.fctrNo
## 0.095363634 -0.088081742
## Q115611.fctrYes Q115899.fctrCs
## 0.285026222 -0.003861343
## Q116881.fctrHappy Q116881.fctrRight
## -0.002832559 0.172117924
## Q98197.fctrNo Q98869.fctrNo
## -0.178871629 -0.118134076
## Q99480.fctrNo Hhold.fctrPKn:.clusterid.fctr2
## -0.077091582 -0.266307387
## Hhold.fctrMKy:.clusterid.fctr4 YOB.Age.fctr(35,40]:YOB.Age.dff
## 0.097377657 -0.001130053
## [1] "max lambda < lambdaOpt:"
## (Intercept) Hhold.fctrMKy
## 2.318858e-01 4.064917e-02
## Hhold.fctrPKn Hhold.fctrPKy
## -2.477206e-01 -9.495962e-02
## Income.fctr.Q Income.fctr^6
## 5.605138e-02 -1.102089e-02
## Q100562.fctrNo Q100689.fctrYes
## -3.743273e-02 -5.207831e-05
## Q101163.fctrDad Q104996.fctrYes
## 1.349664e-01 -1.801455e-03
## Q106272.fctrNo Q106997.fctrGr
## -4.634035e-02 7.822020e-02
## Q108855.fctrYes! Q110740.fctrPC
## 4.982942e-02 8.470511e-02
## Q113181.fctrNo Q113181.fctrYes
## -1.807621e-01 9.776058e-02
## Q115611.fctrNo Q115611.fctrYes
## -8.738496e-02 2.953464e-01
## Q115899.fctrCs Q116881.fctrHappy
## -1.582658e-02 -1.056389e-02
## Q116881.fctrRight Q116953.fctrNo
## 1.782979e-01 1.560789e-02
## Q118232.fctrId Q120472.fctrScience
## -1.082165e-02 1.377212e-02
## Q122120.fctrNo Q98197.fctrNo
## -1.671014e-02 -1.832513e-01
## Q98869.fctrNo Q99480.fctrNo
## -1.326358e-01 -8.793075e-02
## Q99716.fctrYes Hhold.fctrPKn:.clusterid.fctr2
## -1.206254e-03 -3.142328e-01
## Hhold.fctrMKy:.clusterid.fctr4 YOB.Age.fctr(35,40]:YOB.Age.dff
## 1.144192e-01 -8.436593e-03
## [1] "myfit_mdl: train diagnostics complete: 19.758000 secs"
## Prediction
## Reference D R
## D 502 536
## R 395 1026
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 6.213908e-01 2.094839e-01 6.018809e-01 6.406111e-01 5.778772e-01
## AccuracyPValue McnemarPValue
## 6.201681e-06 4.468387e-06
## [1] "myfit_mdl: predict complete: 26.073000 secs"
## id
## 1 Final.All.X##rcv#glmnet
## feats
## 1 Q115611.fctr,Q113181.fctr,Q98197.fctr,Q116881.fctr,Q108855.fctr,Q106272.fctr,Q122771.fctr,Q123621.fctr,Q106388.fctr,Q110740.fctr,Q122769.fctr,Q120472.fctr,Q101596.fctr,Q119334.fctr,Q114152.fctr,Q98869.fctr,Q115899.fctr,Q116797.fctr,Q118232.fctr,Gender.fctr,Q105655.fctr,Q99480.fctr,Q123464.fctr,Q120650.fctr,Q122120.fctr,Q107869.fctr,Q120014.fctr,Q102289.fctr,Income.fctr,Q122770.fctr,Q111580.fctr,Q116601.fctr,Q117186.fctr,Q106993.fctr,Q112270.fctr,Q101162.fctr,Q108856.fctr,Q117193.fctr,Q116441.fctr,Q119851.fctr,Q111848.fctr,Q98578.fctr,Q118892.fctr,Q114386.fctr,Q120978.fctr,Q112512.fctr,Q102674.fctr,Q96024.fctr,Q108950.fctr,Q115610.fctr,YOB.Age.fctr,Q112478.fctr,Q116197.fctr,Q124742.fctr,Q106389.fctr,Edn.fctr,Q118117.fctr,Q100562.fctr,Q107491.fctr,Q116448.fctr,Q108754.fctr,Q116953.fctr,Q115602.fctr,Q118233.fctr,Q120012.fctr,Q118237.fctr,Q99581.fctr,.rnorm,Q120194.fctr,Q115777.fctr,Q106997.fctr,Q100680.fctr,Q113584.fctr,Q108343.fctr,Q121700.fctr,Q105840.fctr,Q120379.fctr,Q103293.fctr,Q124122.fctr,Q109367.fctr,Q113992.fctr,Q121699.fctr,Q121011.fctr,Q114748.fctr,Q106042.fctr,Q111220.fctr,Q114517.fctr,Q102687.fctr,Q102906.fctr,Q98078.fctr,Q115390.fctr,Q102089.fctr,Q100010.fctr,Q99982.fctr,Q113583.fctr,Q108342.fctr,Q104996.fctr,Q119650.fctr,Q100689.fctr,Q108617.fctr,Q115195.fctr,Q99716.fctr,Q101163.fctr,Q98059.fctr,Q114961.fctr,Hhold.fctr,Hhold.fctr:.clusterid.fctr,YOB.Age.fctr:YOB.Age.dff
## max.nTuningRuns min.elapsedtime.everything min.elapsedtime.final
## 1 25 18.334 1.773
## max.AUCpROC.fit max.Sens.fit max.Spec.fit max.AUCROCR.fit
## 1 0.5699133 0.2890173 0.8508093 0.652588
## opt.prob.threshold.fit max.f.score.fit max.Accuracy.fit
## 1 0.55 0.6878981 0.6003805
## max.AccuracyLower.fit max.AccuracyUpper.fit max.Kappa.fit
## 1 0.6018809 0.6406111 0.1204087
## max.AccuracySD.fit max.KappaSD.fit
## 1 0.01449443 0.02968751
## [1] "myfit_mdl: exit: 26.094000 secs"rm(ret_lst)
glb_chunks_df <- myadd_chunk(glb_chunks_df, "fit.data.training", major.inc=FALSE)## label step_major step_minor label_minor bgn end
## 18 fit.data.training 8 0 0 213.910 240.508
## 19 fit.data.training 8 1 1 240.509 NA
## elapsed
## 18 26.598
## 19 NA#stop(here"); glb2Sav()
if (glb_is_classification && glb_is_binomial)
prob_threshold <- glb_models_df[glb_models_df$id == glbMdlSelId,
"opt.prob.threshold.OOB"] else
prob_threshold <- NULL
if (grepl("Ensemble", glbMdlFinId)) {
# Get predictions for each model in ensemble; Outliers that have been moved to OOB might not have been predicted yet
mdlEnsembleComps <- unlist(str_split(subset(glb_models_df,
id == glbMdlFinId)$feats, ","))
if (glb_is_classification)
# mdlEnsembleComps <- gsub("\\.prob$", "", mdlEnsembleComps)
# mdlEnsembleComps <- gsub(paste0("^",
# gsub(".", "\\.", mygetPredictIds(glb_rsp_var)$value, fixed = TRUE)),
# "", mdlEnsembleComps)
mdlEnsembleComps <- glb_models_df$id[sapply(glb_models_df$id, function(thsMdlId)
mygetPredictIds(glb_rsp_var, thsMdlId)$prob %in% mdlEnsembleComps)] else
mdlEnsembleComps <- glb_models_df$id[sapply(glb_models_df$id, function(thsMdlId)
mygetPredictIds(glb_rsp_var, thsMdlId)$value %in% mdlEnsembleComps)]
for (mdl_id in mdlEnsembleComps) {
glbObsTrn <- glb_get_predictions(df = glbObsTrn, mdl_id = mdl_id,
rsp_var = glb_rsp_var,
prob_threshold_def = prob_threshold)
glbObsNew <- glb_get_predictions(df = glbObsNew, mdl_id = mdl_id,
rsp_var = glb_rsp_var,
prob_threshold_def = prob_threshold)
# glb_fin_mdl uses the same coefficients as glb_sel_mdl,
# so copy the "Final" columns into "non-Final" columns
glbObsTrn[, gsub("Final.", "", unlist(mygetPredictIds(glb_rsp_var, mdl_id)))] <-
glbObsTrn[, unlist(mygetPredictIds(glb_rsp_var, mdl_id))]
glbObsNew[, gsub("Final.", "", unlist(mygetPredictIds(glb_rsp_var, mdl_id)))] <-
glbObsNew[, unlist(mygetPredictIds(glb_rsp_var, mdl_id))]
}
}
glbObsTrn <- glb_get_predictions(df = glbObsTrn, mdl_id = glbMdlFinId,
rsp_var = glb_rsp_var,
prob_threshold_def = prob_threshold)## Warning in glb_get_predictions(df = glbObsTrn, mdl_id = glbMdlFinId,
## rsp_var = glb_rsp_var, : Using default probability threshold: 0.55glb_featsimp_df <- myget_feats_importance(mdl=glb_fin_mdl,
featsimp_df=glb_featsimp_df)
#glb_featsimp_df[, paste0(glbMdlFinId, ".imp")] <- glb_featsimp_df$imp
print(glb_featsimp_df)## All.X..rcv.glmnet.imp
## Q115611.fctrYes 52.729697
## Hhold.fctrPKn:.clusterid.fctr2 0.000000
## Hhold.fctrPKn 100.000000
## Q98197.fctrNo 40.627886
## Q113181.fctrNo 51.264404
## Q116881.fctrRight 23.579086
## Q101163.fctrDad 27.773431
## Q98869.fctrNo 5.552206
## Hhold.fctrMKy:.clusterid.fctr4 0.000000
## Q113181.fctrYes 64.984274
## Q115611.fctrNo 44.707621
## Q99480.fctrNo 6.082982
## Q110740.fctrPC 11.933368
## Q106997.fctrGr 15.677653
## Hhold.fctrPKy 17.918579
## Income.fctr.Q 5.630958
## Q108855.fctrYes! 0.000000
## Q106272.fctrNo 0.000000
## Hhold.fctrMKy 25.424438
## Q100562.fctrNo 9.122468
## Q115899.fctrCs 5.392219
## Q122120.fctrNo 0.000000
## Q116953.fctrNo 0.000000
## Q120472.fctrScience 0.000000
## Q116881.fctrHappy 3.039743
## Income.fctr^6 0.000000
## Q118232.fctrId 0.000000
## YOB.Age.fctr(35,40]:YOB.Age.dff 0.000000
## Q104996.fctrYes 0.000000
## Q99716.fctrYes 0.000000
## Q100689.fctrYes 0.000000
## .rnorm 0.000000
## Edn.fctr.C 0.000000
## Edn.fctr.L 0.000000
## Edn.fctr.Q 0.000000
## Edn.fctr^4 0.000000
## Edn.fctr^5 0.000000
## Edn.fctr^6 0.000000
## Edn.fctr^7 0.000000
## Gender.fctrF 0.000000
## Gender.fctrM 0.000000
## Hhold.fctrMKn 0.000000
## Hhold.fctrMKn:.clusterid.fctr2 0.000000
## Hhold.fctrMKn:.clusterid.fctr3 0.000000
## Hhold.fctrMKn:.clusterid.fctr4 0.000000
## Hhold.fctrMKy:.clusterid.fctr2 0.000000
## Hhold.fctrMKy:.clusterid.fctr3 0.000000
## Hhold.fctrN:.clusterid.fctr2 0.000000
## Hhold.fctrN:.clusterid.fctr3 0.000000
## Hhold.fctrN:.clusterid.fctr4 0.000000
## Hhold.fctrPKn:.clusterid.fctr3 0.000000
## Hhold.fctrPKn:.clusterid.fctr4 0.000000
## Hhold.fctrPKy:.clusterid.fctr2 0.000000
## Hhold.fctrPKy:.clusterid.fctr3 0.000000
## Hhold.fctrPKy:.clusterid.fctr4 0.000000
## Hhold.fctrSKn 0.000000
## Hhold.fctrSKn:.clusterid.fctr2 0.000000
## Hhold.fctrSKn:.clusterid.fctr3 0.000000
## Hhold.fctrSKn:.clusterid.fctr4 0.000000
## Hhold.fctrSKy 0.000000
## Hhold.fctrSKy:.clusterid.fctr2 0.000000
## Hhold.fctrSKy:.clusterid.fctr3 0.000000
## Hhold.fctrSKy:.clusterid.fctr4 0.000000
## Income.fctr.C 2.839396
## Income.fctr.L 0.000000
## Income.fctr^4 0.000000
## Income.fctr^5 0.000000
## Q100010.fctrNo 0.000000
## Q100010.fctrYes 0.000000
## Q100562.fctrYes 0.000000
## Q100680.fctrNo 0.000000
## Q100680.fctrYes 0.000000
## Q100689.fctrNo 0.000000
## Q101162.fctrOptimist 0.000000
## Q101162.fctrPessimist 0.000000
## Q101163.fctrMom 0.000000
## Q101596.fctrNo 0.000000
## Q101596.fctrYes 0.000000
## Q102089.fctrOwn 0.000000
## Q102089.fctrRent 0.000000
## Q102289.fctrNo 0.000000
## Q102289.fctrYes 0.000000
## Q102674.fctrNo 0.000000
## Q102674.fctrYes 0.000000
## Q102687.fctrNo 0.000000
## Q102687.fctrYes 0.000000
## Q102906.fctrNo 0.000000
## Q102906.fctrYes 0.000000
## Q103293.fctrNo 0.000000
## Q103293.fctrYes 0.000000
## Q104996.fctrNo 0.000000
## Q105655.fctrNo 0.000000
## Q105655.fctrYes 0.000000
## Q105840.fctrNo 0.000000
## Q105840.fctrYes 0.000000
## Q106042.fctrNo 0.000000
## Q106042.fctrYes 0.000000
## Q106272.fctrYes 22.437747
## Q106388.fctrNo 0.000000
## Q106388.fctrYes 0.000000
## Q106389.fctrNo 0.000000
## Q106389.fctrYes 0.000000
## Q106993.fctrNo 0.000000
## Q106993.fctrYes 0.000000
## Q106997.fctrYy 0.000000
## Q107491.fctrNo 0.000000
## Q107491.fctrYes 0.000000
## Q107869.fctrNo 0.000000
## Q107869.fctrYes 0.000000
## Q108342.fctrIn-person 0.000000
## Q108342.fctrOnline 0.000000
## Q108343.fctrNo 0.000000
## Q108343.fctrYes 0.000000
## Q108617.fctrNo 0.000000
## Q108617.fctrYes 0.000000
## Q108754.fctrNo 0.000000
## Q108754.fctrYes 0.000000
## Q108855.fctrUmm... 0.000000
## Q108856.fctrSocialize 0.000000
## Q108856.fctrSpace 0.000000
## Q108950.fctrCautious 0.000000
## Q108950.fctrRisk-friendly 0.000000
## Q109367.fctrNo 0.000000
## Q109367.fctrYes 0.000000
## Q110740.fctrMac 0.000000
## Q111220.fctrNo 0.000000
## Q111220.fctrYes 0.000000
## Q111580.fctrDemanding 0.000000
## Q111580.fctrSupportive 0.000000
## Q111848.fctrNo 0.000000
## Q111848.fctrYes 0.000000
## Q112270.fctrNo 0.000000
## Q112270.fctrYes 0.000000
## Q112478.fctrNo 0.000000
## Q112478.fctrYes 0.000000
## Q112512.fctrNo 0.000000
## Q112512.fctrYes 0.000000
## Q113583.fctrTalk 0.000000
## Q113583.fctrTunes 0.000000
## Q113584.fctrPeople 0.000000
## Q113584.fctrTechnology 0.000000
## Q113992.fctrNo 0.000000
## Q113992.fctrYes 0.000000
## Q114152.fctrNo 0.000000
## Q114152.fctrYes 0.000000
## Q114386.fctrMysterious 0.000000
## Q114386.fctrTMI 0.000000
## Q114517.fctrNo 0.000000
## Q114517.fctrYes 0.000000
## Q114748.fctrNo 0.000000
## Q114748.fctrYes 0.000000
## Q114961.fctrNo 0.000000
## Q114961.fctrYes 0.000000
## Q115195.fctrNo 0.000000
## Q115195.fctrYes 0.000000
## Q115390.fctrNo 0.000000
## Q115390.fctrYes 0.000000
## Q115602.fctrNo 0.000000
## Q115602.fctrYes 0.000000
## Q115610.fctrNo 0.000000
## Q115610.fctrYes 0.000000
## Q115777.fctrEnd 0.000000
## Q115777.fctrStart 0.000000
## Q115899.fctrMe 0.000000
## Q116197.fctrA.M. 0.000000
## Q116197.fctrP.M. 0.000000
## Q116441.fctrNo 0.000000
## Q116441.fctrYes 0.000000
## Q116448.fctrNo 0.000000
## Q116448.fctrYes 0.000000
## Q116601.fctrNo 0.000000
## Q116601.fctrYes 0.000000
## Q116797.fctrNo 0.000000
## Q116797.fctrYes 0.000000
## Q116953.fctrYes 0.000000
## Q117186.fctrCool headed 0.000000
## Q117186.fctrHot headed 0.000000
## Q117193.fctrOdd hours 0.000000
## Q117193.fctrStandard hours 0.000000
## Q118117.fctrNo 0.000000
## Q118117.fctrYes 0.000000
## Q118232.fctrPr 0.000000
## Q118233.fctrNo 0.000000
## Q118233.fctrYes 0.000000
## Q118237.fctrNo 0.000000
## Q118237.fctrYes 0.000000
## Q118892.fctrNo 0.000000
## Q118892.fctrYes 0.000000
## Q119334.fctrNo 0.000000
## Q119334.fctrYes 0.000000
## Q119650.fctrGiving 5.596421
## Q119650.fctrReceiving 1.557860
## Q119851.fctrNo 0.000000
## Q119851.fctrYes 0.000000
## Q120012.fctrNo 0.000000
## Q120012.fctrYes 0.000000
## Q120014.fctrNo 0.000000
## Q120014.fctrYes 0.000000
## Q120194.fctrStudy first 0.000000
## Q120194.fctrTry first 0.000000
## Q120379.fctrNo 0.000000
## Q120379.fctrYes 0.000000
## Q120472.fctrArt 0.000000
## Q120650.fctrNo 0.000000
## Q120650.fctrYes 0.000000
## Q120978.fctrNo 0.000000
## Q120978.fctrYes 0.000000
## Q121011.fctrNo 0.000000
## Q121011.fctrYes 0.000000
## Q121699.fctrNo 0.000000
## Q121699.fctrYes 0.000000
## Q121700.fctrNo 0.000000
## Q121700.fctrYes 0.000000
## Q122120.fctrYes 0.000000
## Q122769.fctrNo 0.000000
## Q122769.fctrYes 0.000000
## Q122770.fctrNo 0.000000
## Q122770.fctrYes 0.000000
## Q122771.fctrPc 0.000000
## Q122771.fctrPt 0.000000
## Q123464.fctrNo 0.000000
## Q123464.fctrYes 0.000000
## Q123621.fctrNo 0.000000
## Q123621.fctrYes 0.000000
## Q124122.fctrNo 0.000000
## Q124122.fctrYes 0.000000
## Q124742.fctrNo 0.000000
## Q124742.fctrYes 0.000000
## Q96024.fctrNo 0.000000
## Q96024.fctrYes 0.000000
## Q98059.fctrOnly-child 0.000000
## Q98059.fctrYes 0.000000
## Q98078.fctrNo 0.000000
## Q98078.fctrYes 0.000000
## Q98197.fctrYes 0.000000
## Q98578.fctrNo 0.000000
## Q98578.fctrYes 0.000000
## Q98869.fctrYes 0.000000
## Q99480.fctrYes 0.000000
## Q99581.fctrNo 0.000000
## Q99581.fctrYes 0.000000
## Q99716.fctrNo 0.000000
## Q99982.fctrCheck! 0.000000
## Q99982.fctrNope 0.000000
## YOB.Age.fctr(15,20]:YOB.Age.dff 0.000000
## YOB.Age.fctr(20,25]:YOB.Age.dff 0.000000
## YOB.Age.fctr(25,30]:YOB.Age.dff 0.000000
## YOB.Age.fctr(30,35]:YOB.Age.dff 0.000000
## YOB.Age.fctr(40,50]:YOB.Age.dff 0.000000
## YOB.Age.fctr(50,65]:YOB.Age.dff 0.000000
## YOB.Age.fctr(65,90]:YOB.Age.dff 0.000000
## YOB.Age.fctr.C 0.000000
## YOB.Age.fctr.L 0.000000
## YOB.Age.fctr.Q 0.000000
## YOB.Age.fctrNA:YOB.Age.dff 0.000000
## YOB.Age.fctr^4 0.000000
## YOB.Age.fctr^5 0.000000
## YOB.Age.fctr^6 0.000000
## YOB.Age.fctr^7 0.000000
## YOB.Age.fctr^8 0.000000
## Final.All.X..rcv.glmnet.imp imp
## Q115611.fctrYes 1.000000e+02 1.000000e+02
## Hhold.fctrPKn:.clusterid.fctr2 9.986214e+01 9.986214e+01
## Hhold.fctrPKn 8.186284e+01 8.186284e+01
## Q98197.fctrNo 6.240403e+01 6.240403e+01
## Q113181.fctrNo 6.158911e+01 6.158911e+01
## Q116881.fctrRight 6.037796e+01 6.037796e+01
## Q101163.fctrDad 4.478129e+01 4.478129e+01
## Q98869.fctrNo 4.316389e+01 4.316389e+01
## Hhold.fctrMKy:.clusterid.fctr4 3.643439e+01 3.643439e+01
## Q113181.fctrYes 3.328050e+01 3.328050e+01
## Q115611.fctrNo 3.025038e+01 3.025038e+01
## Q99480.fctrNo 2.839881e+01 2.839881e+01
## Q110740.fctrPC 2.695620e+01 2.695620e+01
## Q106997.fctrGr 2.373294e+01 2.373294e+01
## Hhold.fctrPKy 2.171103e+01 2.171103e+01
## Income.fctr.Q 1.636844e+01 1.636844e+01
## Q108855.fctrYes! 1.506953e+01 1.506953e+01
## Q106272.fctrNo 1.395534e+01 1.395534e+01
## Hhold.fctrMKy 1.275156e+01 1.275156e+01
## Q100562.fctrNo 9.501393e+00 9.501393e+00
## Q115899.fctrCs 3.340786e+00 3.340786e+00
## Q122120.fctrNo 2.806431e+00 2.806431e+00
## Q116953.fctrNo 2.621310e+00 2.621310e+00
## Q120472.fctrScience 2.312996e+00 2.312996e+00
## Q116881.fctrHappy 2.275023e+00 2.275023e+00
## Income.fctr^6 1.850934e+00 1.850934e+00
## Q118232.fctrId 1.817472e+00 1.817472e+00
## YOB.Age.fctr(35,40]:YOB.Age.dff 1.616719e+00 1.616719e+00
## Q104996.fctrYes 3.025503e-01 3.025503e-01
## Q99716.fctrYes 2.025877e-01 2.025877e-01
## Q100689.fctrYes 8.746435e-03 8.746435e-03
## .rnorm 0.000000e+00 0.000000e+00
## Edn.fctr.C 0.000000e+00 0.000000e+00
## Edn.fctr.L 0.000000e+00 0.000000e+00
## Edn.fctr.Q 0.000000e+00 0.000000e+00
## Edn.fctr^4 0.000000e+00 0.000000e+00
## Edn.fctr^5 0.000000e+00 0.000000e+00
## Edn.fctr^6 0.000000e+00 0.000000e+00
## Edn.fctr^7 0.000000e+00 0.000000e+00
## Gender.fctrF 0.000000e+00 0.000000e+00
## Gender.fctrM 0.000000e+00 0.000000e+00
## Hhold.fctrMKn 0.000000e+00 0.000000e+00
## Hhold.fctrMKn:.clusterid.fctr2 0.000000e+00 0.000000e+00
## Hhold.fctrMKn:.clusterid.fctr3 0.000000e+00 0.000000e+00
## Hhold.fctrMKn:.clusterid.fctr4 0.000000e+00 0.000000e+00
## Hhold.fctrMKy:.clusterid.fctr2 0.000000e+00 0.000000e+00
## Hhold.fctrMKy:.clusterid.fctr3 0.000000e+00 0.000000e+00
## Hhold.fctrN:.clusterid.fctr2 0.000000e+00 0.000000e+00
## Hhold.fctrN:.clusterid.fctr3 0.000000e+00 0.000000e+00
## Hhold.fctrN:.clusterid.fctr4 0.000000e+00 0.000000e+00
## Hhold.fctrPKn:.clusterid.fctr3 0.000000e+00 0.000000e+00
## Hhold.fctrPKn:.clusterid.fctr4 0.000000e+00 0.000000e+00
## Hhold.fctrPKy:.clusterid.fctr2 0.000000e+00 0.000000e+00
## Hhold.fctrPKy:.clusterid.fctr3 0.000000e+00 0.000000e+00
## Hhold.fctrPKy:.clusterid.fctr4 0.000000e+00 0.000000e+00
## Hhold.fctrSKn 0.000000e+00 0.000000e+00
## Hhold.fctrSKn:.clusterid.fctr2 0.000000e+00 0.000000e+00
## Hhold.fctrSKn:.clusterid.fctr3 0.000000e+00 0.000000e+00
## Hhold.fctrSKn:.clusterid.fctr4 0.000000e+00 0.000000e+00
## Hhold.fctrSKy 0.000000e+00 0.000000e+00
## Hhold.fctrSKy:.clusterid.fctr2 0.000000e+00 0.000000e+00
## Hhold.fctrSKy:.clusterid.fctr3 0.000000e+00 0.000000e+00
## Hhold.fctrSKy:.clusterid.fctr4 0.000000e+00 0.000000e+00
## Income.fctr.C 0.000000e+00 0.000000e+00
## Income.fctr.L 0.000000e+00 0.000000e+00
## Income.fctr^4 0.000000e+00 0.000000e+00
## Income.fctr^5 0.000000e+00 0.000000e+00
## Q100010.fctrNo 0.000000e+00 0.000000e+00
## Q100010.fctrYes 0.000000e+00 0.000000e+00
## Q100562.fctrYes 0.000000e+00 0.000000e+00
## Q100680.fctrNo 0.000000e+00 0.000000e+00
## Q100680.fctrYes 0.000000e+00 0.000000e+00
## Q100689.fctrNo 0.000000e+00 0.000000e+00
## Q101162.fctrOptimist 0.000000e+00 0.000000e+00
## Q101162.fctrPessimist 0.000000e+00 0.000000e+00
## Q101163.fctrMom 0.000000e+00 0.000000e+00
## Q101596.fctrNo 0.000000e+00 0.000000e+00
## Q101596.fctrYes 0.000000e+00 0.000000e+00
## Q102089.fctrOwn 0.000000e+00 0.000000e+00
## Q102089.fctrRent 0.000000e+00 0.000000e+00
## Q102289.fctrNo 0.000000e+00 0.000000e+00
## Q102289.fctrYes 0.000000e+00 0.000000e+00
## Q102674.fctrNo 0.000000e+00 0.000000e+00
## Q102674.fctrYes 0.000000e+00 0.000000e+00
## Q102687.fctrNo 0.000000e+00 0.000000e+00
## Q102687.fctrYes 0.000000e+00 0.000000e+00
## Q102906.fctrNo 0.000000e+00 0.000000e+00
## Q102906.fctrYes 0.000000e+00 0.000000e+00
## Q103293.fctrNo 0.000000e+00 0.000000e+00
## Q103293.fctrYes 0.000000e+00 0.000000e+00
## Q104996.fctrNo 0.000000e+00 0.000000e+00
## Q105655.fctrNo 0.000000e+00 0.000000e+00
## Q105655.fctrYes 0.000000e+00 0.000000e+00
## Q105840.fctrNo 0.000000e+00 0.000000e+00
## Q105840.fctrYes 0.000000e+00 0.000000e+00
## Q106042.fctrNo 0.000000e+00 0.000000e+00
## Q106042.fctrYes 0.000000e+00 0.000000e+00
## Q106272.fctrYes 0.000000e+00 0.000000e+00
## Q106388.fctrNo 0.000000e+00 0.000000e+00
## Q106388.fctrYes 0.000000e+00 0.000000e+00
## Q106389.fctrNo 0.000000e+00 0.000000e+00
## Q106389.fctrYes 0.000000e+00 0.000000e+00
## Q106993.fctrNo 0.000000e+00 0.000000e+00
## Q106993.fctrYes 0.000000e+00 0.000000e+00
## Q106997.fctrYy 0.000000e+00 0.000000e+00
## Q107491.fctrNo 0.000000e+00 0.000000e+00
## Q107491.fctrYes 0.000000e+00 0.000000e+00
## Q107869.fctrNo 0.000000e+00 0.000000e+00
## Q107869.fctrYes 0.000000e+00 0.000000e+00
## Q108342.fctrIn-person 0.000000e+00 0.000000e+00
## Q108342.fctrOnline 0.000000e+00 0.000000e+00
## Q108343.fctrNo 0.000000e+00 0.000000e+00
## Q108343.fctrYes 0.000000e+00 0.000000e+00
## Q108617.fctrNo 0.000000e+00 0.000000e+00
## Q108617.fctrYes 0.000000e+00 0.000000e+00
## Q108754.fctrNo 0.000000e+00 0.000000e+00
## Q108754.fctrYes 0.000000e+00 0.000000e+00
## Q108855.fctrUmm... 0.000000e+00 0.000000e+00
## Q108856.fctrSocialize 0.000000e+00 0.000000e+00
## Q108856.fctrSpace 0.000000e+00 0.000000e+00
## Q108950.fctrCautious 0.000000e+00 0.000000e+00
## Q108950.fctrRisk-friendly 0.000000e+00 0.000000e+00
## Q109367.fctrNo 0.000000e+00 0.000000e+00
## Q109367.fctrYes 0.000000e+00 0.000000e+00
## Q110740.fctrMac 0.000000e+00 0.000000e+00
## Q111220.fctrNo 0.000000e+00 0.000000e+00
## Q111220.fctrYes 0.000000e+00 0.000000e+00
## Q111580.fctrDemanding 0.000000e+00 0.000000e+00
## Q111580.fctrSupportive 0.000000e+00 0.000000e+00
## Q111848.fctrNo 0.000000e+00 0.000000e+00
## Q111848.fctrYes 0.000000e+00 0.000000e+00
## Q112270.fctrNo 0.000000e+00 0.000000e+00
## Q112270.fctrYes 0.000000e+00 0.000000e+00
## Q112478.fctrNo 0.000000e+00 0.000000e+00
## Q112478.fctrYes 0.000000e+00 0.000000e+00
## Q112512.fctrNo 0.000000e+00 0.000000e+00
## Q112512.fctrYes 0.000000e+00 0.000000e+00
## Q113583.fctrTalk 0.000000e+00 0.000000e+00
## Q113583.fctrTunes 0.000000e+00 0.000000e+00
## Q113584.fctrPeople 0.000000e+00 0.000000e+00
## Q113584.fctrTechnology 0.000000e+00 0.000000e+00
## Q113992.fctrNo 0.000000e+00 0.000000e+00
## Q113992.fctrYes 0.000000e+00 0.000000e+00
## Q114152.fctrNo 0.000000e+00 0.000000e+00
## Q114152.fctrYes 0.000000e+00 0.000000e+00
## Q114386.fctrMysterious 0.000000e+00 0.000000e+00
## Q114386.fctrTMI 0.000000e+00 0.000000e+00
## Q114517.fctrNo 0.000000e+00 0.000000e+00
## Q114517.fctrYes 0.000000e+00 0.000000e+00
## Q114748.fctrNo 0.000000e+00 0.000000e+00
## Q114748.fctrYes 0.000000e+00 0.000000e+00
## Q114961.fctrNo 0.000000e+00 0.000000e+00
## Q114961.fctrYes 0.000000e+00 0.000000e+00
## Q115195.fctrNo 0.000000e+00 0.000000e+00
## Q115195.fctrYes 0.000000e+00 0.000000e+00
## Q115390.fctrNo 0.000000e+00 0.000000e+00
## Q115390.fctrYes 0.000000e+00 0.000000e+00
## Q115602.fctrNo 0.000000e+00 0.000000e+00
## Q115602.fctrYes 0.000000e+00 0.000000e+00
## Q115610.fctrNo 0.000000e+00 0.000000e+00
## Q115610.fctrYes 0.000000e+00 0.000000e+00
## Q115777.fctrEnd 0.000000e+00 0.000000e+00
## Q115777.fctrStart 0.000000e+00 0.000000e+00
## Q115899.fctrMe 0.000000e+00 0.000000e+00
## Q116197.fctrA.M. 0.000000e+00 0.000000e+00
## Q116197.fctrP.M. 0.000000e+00 0.000000e+00
## Q116441.fctrNo 0.000000e+00 0.000000e+00
## Q116441.fctrYes 0.000000e+00 0.000000e+00
## Q116448.fctrNo 0.000000e+00 0.000000e+00
## Q116448.fctrYes 0.000000e+00 0.000000e+00
## Q116601.fctrNo 0.000000e+00 0.000000e+00
## Q116601.fctrYes 0.000000e+00 0.000000e+00
## Q116797.fctrNo 0.000000e+00 0.000000e+00
## Q116797.fctrYes 0.000000e+00 0.000000e+00
## Q116953.fctrYes 0.000000e+00 0.000000e+00
## Q117186.fctrCool headed 0.000000e+00 0.000000e+00
## Q117186.fctrHot headed 0.000000e+00 0.000000e+00
## Q117193.fctrOdd hours 0.000000e+00 0.000000e+00
## Q117193.fctrStandard hours 0.000000e+00 0.000000e+00
## Q118117.fctrNo 0.000000e+00 0.000000e+00
## Q118117.fctrYes 0.000000e+00 0.000000e+00
## Q118232.fctrPr 0.000000e+00 0.000000e+00
## Q118233.fctrNo 0.000000e+00 0.000000e+00
## Q118233.fctrYes 0.000000e+00 0.000000e+00
## Q118237.fctrNo 0.000000e+00 0.000000e+00
## Q118237.fctrYes 0.000000e+00 0.000000e+00
## Q118892.fctrNo 0.000000e+00 0.000000e+00
## Q118892.fctrYes 0.000000e+00 0.000000e+00
## Q119334.fctrNo 0.000000e+00 0.000000e+00
## Q119334.fctrYes 0.000000e+00 0.000000e+00
## Q119650.fctrGiving 0.000000e+00 0.000000e+00
## Q119650.fctrReceiving 0.000000e+00 0.000000e+00
## Q119851.fctrNo 0.000000e+00 0.000000e+00
## Q119851.fctrYes 0.000000e+00 0.000000e+00
## Q120012.fctrNo 0.000000e+00 0.000000e+00
## Q120012.fctrYes 0.000000e+00 0.000000e+00
## Q120014.fctrNo 0.000000e+00 0.000000e+00
## Q120014.fctrYes 0.000000e+00 0.000000e+00
## Q120194.fctrStudy first 0.000000e+00 0.000000e+00
## Q120194.fctrTry first 0.000000e+00 0.000000e+00
## Q120379.fctrNo 0.000000e+00 0.000000e+00
## Q120379.fctrYes 0.000000e+00 0.000000e+00
## Q120472.fctrArt 0.000000e+00 0.000000e+00
## Q120650.fctrNo 0.000000e+00 0.000000e+00
## Q120650.fctrYes 0.000000e+00 0.000000e+00
## Q120978.fctrNo 0.000000e+00 0.000000e+00
## Q120978.fctrYes 0.000000e+00 0.000000e+00
## Q121011.fctrNo 0.000000e+00 0.000000e+00
## Q121011.fctrYes 0.000000e+00 0.000000e+00
## Q121699.fctrNo 0.000000e+00 0.000000e+00
## Q121699.fctrYes 0.000000e+00 0.000000e+00
## Q121700.fctrNo 0.000000e+00 0.000000e+00
## Q121700.fctrYes 0.000000e+00 0.000000e+00
## Q122120.fctrYes 0.000000e+00 0.000000e+00
## Q122769.fctrNo 0.000000e+00 0.000000e+00
## Q122769.fctrYes 0.000000e+00 0.000000e+00
## Q122770.fctrNo 0.000000e+00 0.000000e+00
## Q122770.fctrYes 0.000000e+00 0.000000e+00
## Q122771.fctrPc 0.000000e+00 0.000000e+00
## Q122771.fctrPt 0.000000e+00 0.000000e+00
## Q123464.fctrNo 0.000000e+00 0.000000e+00
## Q123464.fctrYes 0.000000e+00 0.000000e+00
## Q123621.fctrNo 0.000000e+00 0.000000e+00
## Q123621.fctrYes 0.000000e+00 0.000000e+00
## Q124122.fctrNo 0.000000e+00 0.000000e+00
## Q124122.fctrYes 0.000000e+00 0.000000e+00
## Q124742.fctrNo 0.000000e+00 0.000000e+00
## Q124742.fctrYes 0.000000e+00 0.000000e+00
## Q96024.fctrNo 0.000000e+00 0.000000e+00
## Q96024.fctrYes 0.000000e+00 0.000000e+00
## Q98059.fctrOnly-child 0.000000e+00 0.000000e+00
## Q98059.fctrYes 0.000000e+00 0.000000e+00
## Q98078.fctrNo 0.000000e+00 0.000000e+00
## Q98078.fctrYes 0.000000e+00 0.000000e+00
## Q98197.fctrYes 0.000000e+00 0.000000e+00
## Q98578.fctrNo 0.000000e+00 0.000000e+00
## Q98578.fctrYes 0.000000e+00 0.000000e+00
## Q98869.fctrYes 0.000000e+00 0.000000e+00
## Q99480.fctrYes 0.000000e+00 0.000000e+00
## Q99581.fctrNo 0.000000e+00 0.000000e+00
## Q99581.fctrYes 0.000000e+00 0.000000e+00
## Q99716.fctrNo 0.000000e+00 0.000000e+00
## Q99982.fctrCheck! 0.000000e+00 0.000000e+00
## Q99982.fctrNope 0.000000e+00 0.000000e+00
## YOB.Age.fctr(15,20]:YOB.Age.dff 0.000000e+00 0.000000e+00
## YOB.Age.fctr(20,25]:YOB.Age.dff 0.000000e+00 0.000000e+00
## YOB.Age.fctr(25,30]:YOB.Age.dff 0.000000e+00 0.000000e+00
## YOB.Age.fctr(30,35]:YOB.Age.dff 0.000000e+00 0.000000e+00
## YOB.Age.fctr(40,50]:YOB.Age.dff 0.000000e+00 0.000000e+00
## YOB.Age.fctr(50,65]:YOB.Age.dff 0.000000e+00 0.000000e+00
## YOB.Age.fctr(65,90]:YOB.Age.dff 0.000000e+00 0.000000e+00
## YOB.Age.fctr.C 0.000000e+00 0.000000e+00
## YOB.Age.fctr.L 0.000000e+00 0.000000e+00
## YOB.Age.fctr.Q 0.000000e+00 0.000000e+00
## YOB.Age.fctrNA:YOB.Age.dff 0.000000e+00 0.000000e+00
## YOB.Age.fctr^4 0.000000e+00 0.000000e+00
## YOB.Age.fctr^5 0.000000e+00 0.000000e+00
## YOB.Age.fctr^6 0.000000e+00 0.000000e+00
## YOB.Age.fctr^7 0.000000e+00 0.000000e+00
## YOB.Age.fctr^8 0.000000e+00 0.000000e+00if (glb_is_classification && glb_is_binomial)
glb_analytics_diag_plots(obs_df=glbObsTrn, mdl_id=glbMdlFinId,
prob_threshold=glb_models_df[glb_models_df$id == glbMdlSelId,
"opt.prob.threshold.OOB"]) else
glb_analytics_diag_plots(obs_df=glbObsTrn, mdl_id=glbMdlFinId) ## Warning in glb_analytics_diag_plots(obs_df = glbObsTrn, mdl_id =
## glbMdlFinId, : Limiting important feature scatter plots to 5 out of 108
## [1] "Min/Max Boundaries: "
## [1] "Inaccurate: "
## USER_ID Party.fctr Party.fctr.All.X..rcv.glmnet.prob
## 1 5879 R 0.3800821
## 2 26 R 0.3768542
## 3 1610 R 0.4077182
## 4 403 R 0.4329510
## 5 895 R 0.4374456
## 6 660 R 0.4670456
## Party.fctr.All.X..rcv.glmnet Party.fctr.All.X..rcv.glmnet.err
## 1 D TRUE
## 2 D TRUE
## 3 D TRUE
## 4 D TRUE
## 5 D TRUE
## 6 D TRUE
## Party.fctr.All.X..rcv.glmnet.err.abs Party.fctr.All.X..rcv.glmnet.is.acc
## 1 0.6199179 FALSE
## 2 0.6231458 FALSE
## 3 0.5922818 FALSE
## 4 0.5670490 FALSE
## 5 0.5625544 FALSE
## 6 0.5329544 FALSE
## Party.fctr.Final.All.X..rcv.glmnet.prob
## 1 0.3859256
## 2 0.3890654
## 3 0.3932298
## 4 0.3947726
## 5 0.4064961
## 6 0.4076968
## Party.fctr.Final.All.X..rcv.glmnet
## 1 D
## 2 D
## 3 D
## 4 D
## 5 D
## 6 D
## Party.fctr.Final.All.X..rcv.glmnet.err
## 1 TRUE
## 2 TRUE
## 3 TRUE
## 4 TRUE
## 5 TRUE
## 6 TRUE
## Party.fctr.Final.All.X..rcv.glmnet.err.abs
## 1 0.6140744
## 2 0.6109346
## 3 0.6067702
## 4 0.6052274
## 5 0.5935039
## 6 0.5923032
## Party.fctr.Final.All.X..rcv.glmnet.is.acc
## 1 FALSE
## 2 FALSE
## 3 FALSE
## 4 FALSE
## 5 FALSE
## 6 FALSE
## Party.fctr.Final.All.X..rcv.glmnet.accurate
## 1 FALSE
## 2 FALSE
## 3 FALSE
## 4 FALSE
## 5 FALSE
## 6 FALSE
## Party.fctr.Final.All.X..rcv.glmnet.error
## 1 -0.1640744
## 2 -0.1609346
## 3 -0.1567702
## 4 -0.1552274
## 5 -0.1435039
## 6 -0.1423032
## USER_ID Party.fctr Party.fctr.All.X..rcv.glmnet.prob
## 21 1275 R NA
## 38 5089 R 0.4501006
## 446 6011 D NA
## 474 1769 D 0.5826074
## 535 1182 D 0.5892904
## 916 5452 D 0.7010340
## Party.fctr.All.X..rcv.glmnet Party.fctr.All.X..rcv.glmnet.err
## 21 <NA> NA
## 38 D TRUE
## 446 <NA> NA
## 474 R TRUE
## 535 R TRUE
## 916 R TRUE
## Party.fctr.All.X..rcv.glmnet.err.abs
## 21 NA
## 38 0.5498994
## 446 NA
## 474 0.5826074
## 535 0.5892904
## 916 0.7010340
## Party.fctr.All.X..rcv.glmnet.is.acc
## 21 NA
## 38 FALSE
## 446 NA
## 474 FALSE
## 535 FALSE
## 916 FALSE
## Party.fctr.Final.All.X..rcv.glmnet.prob
## 21 0.4300139
## 38 0.4427751
## 446 0.5581125
## 474 0.5629623
## 535 0.5748162
## 916 0.7215536
## Party.fctr.Final.All.X..rcv.glmnet
## 21 D
## 38 D
## 446 R
## 474 R
## 535 R
## 916 R
## Party.fctr.Final.All.X..rcv.glmnet.err
## 21 TRUE
## 38 TRUE
## 446 TRUE
## 474 TRUE
## 535 TRUE
## 916 TRUE
## Party.fctr.Final.All.X..rcv.glmnet.err.abs
## 21 0.5699861
## 38 0.5572249
## 446 0.5581125
## 474 0.5629623
## 535 0.5748162
## 916 0.7215536
## Party.fctr.Final.All.X..rcv.glmnet.is.acc
## 21 FALSE
## 38 FALSE
## 446 FALSE
## 474 FALSE
## 535 FALSE
## 916 FALSE
## Party.fctr.Final.All.X..rcv.glmnet.accurate
## 21 FALSE
## 38 FALSE
## 446 FALSE
## 474 FALSE
## 535 FALSE
## 916 FALSE
## Party.fctr.Final.All.X..rcv.glmnet.error
## 21 -0.119986086
## 38 -0.107224923
## 446 0.008112456
## 474 0.012962265
## 535 0.024816175
## 916 0.171553560
## USER_ID Party.fctr Party.fctr.All.X..rcv.glmnet.prob
## 926 2641 D 0.7193139
## 927 4956 D NA
## 928 3474 D 0.7270990
## 929 78 D 0.7414410
## 930 1309 D 0.7418801
## 931 3578 D 0.7371386
## Party.fctr.All.X..rcv.glmnet Party.fctr.All.X..rcv.glmnet.err
## 926 R TRUE
## 927 <NA> NA
## 928 R TRUE
## 929 R TRUE
## 930 R TRUE
## 931 R TRUE
## Party.fctr.All.X..rcv.glmnet.err.abs
## 926 0.7193139
## 927 NA
## 928 0.7270990
## 929 0.7414410
## 930 0.7418801
## 931 0.7371386
## Party.fctr.All.X..rcv.glmnet.is.acc
## 926 FALSE
## 927 NA
## 928 FALSE
## 929 FALSE
## 930 FALSE
## 931 FALSE
## Party.fctr.Final.All.X..rcv.glmnet.prob
## 926 0.7325864
## 927 0.7408101
## 928 0.7410468
## 929 0.7411917
## 930 0.7522748
## 931 0.7529558
## Party.fctr.Final.All.X..rcv.glmnet
## 926 R
## 927 R
## 928 R
## 929 R
## 930 R
## 931 R
## Party.fctr.Final.All.X..rcv.glmnet.err
## 926 TRUE
## 927 TRUE
## 928 TRUE
## 929 TRUE
## 930 TRUE
## 931 TRUE
## Party.fctr.Final.All.X..rcv.glmnet.err.abs
## 926 0.7325864
## 927 0.7408101
## 928 0.7410468
## 929 0.7411917
## 930 0.7522748
## 931 0.7529558
## Party.fctr.Final.All.X..rcv.glmnet.is.acc
## 926 FALSE
## 927 FALSE
## 928 FALSE
## 929 FALSE
## 930 FALSE
## 931 FALSE
## Party.fctr.Final.All.X..rcv.glmnet.accurate
## 926 FALSE
## 927 FALSE
## 928 FALSE
## 929 FALSE
## 930 FALSE
## 931 FALSE
## Party.fctr.Final.All.X..rcv.glmnet.error
## 926 0.1825864
## 927 0.1908101
## 928 0.1910468
## 929 0.1911917
## 930 0.2022748
## 931 0.2029558
dsp_feats_vctr <- c(NULL)
for(var in grep(".imp", names(glb_feats_df), fixed=TRUE, value=TRUE))
dsp_feats_vctr <- union(dsp_feats_vctr,
glb_feats_df[!is.na(glb_feats_df[, var]), "id"])
# print(glbObsTrn[glbObsTrn$UniqueID %in% FN_OOB_ids,
# grep(glb_rsp_var, names(glbObsTrn), value=TRUE)])
print(setdiff(names(glbObsTrn), names(glbObsAll)))## [1] "Party.fctr.Final.All.X..rcv.glmnet.prob"
## [2] "Party.fctr.Final.All.X..rcv.glmnet"
## [3] "Party.fctr.Final.All.X..rcv.glmnet.err"
## [4] "Party.fctr.Final.All.X..rcv.glmnet.err.abs"
## [5] "Party.fctr.Final.All.X..rcv.glmnet.is.acc"for (col in setdiff(names(glbObsTrn), names(glbObsAll)))
# Merge or cbind ?
glbObsAll[glbObsAll$.src == "Train", col] <- glbObsTrn[, col]
print(setdiff(names(glbObsFit), names(glbObsAll)))## character(0)print(setdiff(names(glbObsOOB), names(glbObsAll)))## character(0)for (col in setdiff(names(glbObsOOB), names(glbObsAll)))
# Merge or cbind ?
glbObsAll[glbObsAll$.lcn == "OOB", col] <- glbObsOOB[, col]
print(setdiff(names(glbObsNew), names(glbObsAll)))## character(0)#glb2Sav(); all.equal(savObsAll, glbObsAll); all.equal(sav_models_lst, glb_models_lst)
#load(file = paste0(glbOut$pfx, "dsk_knitr.RData"))
#cmpCols <- names(glbObsAll)[!grepl("\\.Final\\.", names(glbObsAll))]; all.equal(savObsAll[, cmpCols], glbObsAll[, cmpCols]); all.equal(savObsAll[, "H.P.http"], glbObsAll[, "H.P.http"]);
replay.petrisim(pn = glb_analytics_pn,
replay.trans = (glb_analytics_avl_objs <- c(glb_analytics_avl_objs,
"data.training.all.prediction","model.final")), flip_coord = TRUE)## time trans "bgn " "fit.data.training.all " "predict.data.new " "end "
## 0.0000 multiple enabled transitions: data.training.all data.new model.selected firing: data.training.all
## 1.0000 1 2 1 0 0
## 1.0000 multiple enabled transitions: data.training.all data.new model.selected model.final data.training.all.prediction firing: data.new
## 2.0000 2 1 1 1 0
## 2.0000 multiple enabled transitions: data.training.all data.new model.selected model.final data.training.all.prediction data.new.prediction firing: model.selected
## 3.0000 3 0 2 1 0
## 3.0000 multiple enabled transitions: model.final data.training.all.prediction data.new.prediction firing: data.training.all.prediction
## 4.0000 5 0 1 1 1
## 4.0000 multiple enabled transitions: model.final data.training.all.prediction data.new.prediction firing: model.final
## 5.0000 4 0 0 2 1
glb_chunks_df <- myadd_chunk(glb_chunks_df, "predict.data.new", major.inc = TRUE)## label step_major step_minor label_minor bgn end
## 19 fit.data.training 8 1 1 240.509 247.589
## 20 predict.data.new 9 0 0 247.589 NA
## elapsed
## 19 7.08
## 20 NAStep 9.0: predict data new
## Warning in glb_get_predictions(obs_df, mdl_id = glbMdlFinId, rsp_var =
## glb_rsp_var, : Using default probability threshold: 0.55
## Warning in glb_get_predictions(obs_df, mdl_id = glbMdlFinId, rsp_var =
## glb_rsp_var, : Using default probability threshold: 0.55## Warning in glb_analytics_diag_plots(obs_df = glbObsNew, mdl_id =
## glbMdlFinId, : Limiting important feature scatter plots to 5 out of 108## Warning: Removed 622 rows containing missing values (geom_point).
## Warning: Removed 622 rows containing missing values (geom_point).
## Warning: Removed 622 rows containing missing values (geom_point).
## Warning: Removed 622 rows containing missing values (geom_point).
## Warning: Removed 622 rows containing missing values (geom_point).
## Warning: Removed 622 rows containing missing values (geom_point).
## Warning: Removed 622 rows containing missing values (geom_point).
## Warning: Removed 622 rows containing missing values (geom_point).
## Warning: Removed 622 rows containing missing values (geom_point).
## Warning: Removed 622 rows containing missing values (geom_point).
## NULL## [1] "OOBobs total range outliers: 0"
## [1] "newobs total range outliers: 0"## [1] "Stacking file Votes_Ensemble_cnk06_out_fin.csv to prediction outputs..."## [1] 0.55## [1] "glbMdlSelId: All.X##rcv#glmnet"## [1] "glbMdlFinId: Final.All.X##rcv#glmnet"## [1] "Cross Validation issues:"
## MFO###myMFO_classfr Random###myrandom_classfr
## 0 0
## Max.cor.Y.rcv.1X1###glmnet
## 0## max.Accuracy.OOB max.AUCROCR.OOB
## All.X##rcv#glmnet 0.5796813 0.5801856
## Low.cor.X##rcv#glmnet 0.5737052 0.5816378
## Max.cor.Y.rcv.1X1###glmnet 0.5737052 0.5592306
## Max.cor.Y##rcv#rpart 0.5737052 0.5325318
## Random###myrandom_classfr 0.5737052 0.5181075
## MFO###myMFO_classfr 0.5737052 0.5000000
## Final.All.X##rcv#glmnet NA NA
## max.AUCpROC.OOB min.elapsedtime.everything
## All.X##rcv#glmnet 0.5067173 15.750
## Low.cor.X##rcv#glmnet 0.5091186 15.497
## Max.cor.Y.rcv.1X1###glmnet 0.5338785 0.721
## Max.cor.Y##rcv#rpart 0.5334729 1.415
## Random###myrandom_classfr 0.4990752 0.266
## MFO###myMFO_classfr 0.5000000 0.473
## Final.All.X##rcv#glmnet NA 18.334
## max.Accuracy.fit opt.prob.threshold.fit
## All.X##rcv#glmnet 0.6055195 0.50
## Low.cor.X##rcv#glmnet 0.6050093 0.50
## Max.cor.Y.rcv.1X1###glmnet 0.6162494 0.55
## Max.cor.Y##rcv#rpart 0.6104535 0.50
## Random###myrandom_classfr 0.5789474 0.40
## MFO###myMFO_classfr 0.5789474 0.40
## Final.All.X##rcv#glmnet 0.6003805 0.55
## opt.prob.threshold.OOB
## All.X##rcv#glmnet 0.55
## Low.cor.X##rcv#glmnet 0.45
## Max.cor.Y.rcv.1X1###glmnet 0.40
## Max.cor.Y##rcv#rpart 0.40
## Random###myrandom_classfr 0.40
## MFO###myMFO_classfr 0.40
## Final.All.X##rcv#glmnet NA## [1] "All.X##rcv#glmnet OOB confusion matrix & accuracy: "
## Prediction
## Reference D R
## D 97 117
## R 94 194## err.abs.fit.sum err.abs.OOB.sum err.abs.trn.sum err.abs.new.sum
## PKy 7.086145 3.238914 10.35792 NA
## PKn 24.399436 6.726635 30.86897 NA
## SKy 28.898436 11.815230 40.37918 NA
## N 54.104346 13.604103 66.70618 NA
## MKn 104.765360 35.796619 139.88924 NA
## SKn 386.381033 95.720498 479.65189 NA
## MKy 308.646219 72.981800 380.01349 NA
## .freqRatio.Fit .freqRatio.OOB .freqRatio.Tst .n.Fit .n.New.D .n.New.R
## PKy 0.007153807 0.01195219 0.009646302 14 3 3
## PKn 0.025549310 0.02589641 0.024115756 50 8 7
## SKy 0.031170158 0.04581673 0.043408360 61 10 17
## N 0.059274400 0.05577689 0.053054662 116 21 12
## MKn 0.115482882 0.14940239 0.151125402 226 19 75
## SKn 0.413898825 0.40039841 0.405144695 810 117 135
## MKy 0.347470618 0.31075697 0.313504823 680 31 164
## .n.OOB .n.Trn.D .n.Trn.R .n.Tst .n.fit .n.new .n.trn err.abs.OOB.mean
## PKy 6 13 7 6 14 6 20 0.5398191
## PKn 13 40 23 15 50 15 63 0.5174334
## SKy 23 43 41 27 61 27 84 0.5137057
## N 28 59 85 33 116 33 144 0.4858608
## MKn 75 123 178 94 226 94 301 0.4772882
## SKn 201 454 557 252 810 252 1011 0.4762214
## MKy 156 306 530 195 680 195 836 0.4678321
## err.abs.fit.mean err.abs.new.mean err.abs.trn.mean
## PKy 0.5061532 NA 0.5178958
## PKn 0.4879887 NA 0.4899836
## SKy 0.4737449 NA 0.4807045
## N 0.4664168 NA 0.4632373
## MKn 0.4635635 NA 0.4647483
## SKn 0.4770136 NA 0.4744331
## MKy 0.4538915 NA 0.4545616
## err.abs.fit.sum err.abs.OOB.sum err.abs.trn.sum err.abs.new.sum
## 914.280975 239.883799 1147.866857 NA
## .freqRatio.Fit .freqRatio.OOB .freqRatio.Tst .n.Fit
## 1.000000 1.000000 1.000000 1957.000000
## .n.New.D .n.New.R .n.OOB .n.Trn.D
## 209.000000 413.000000 502.000000 1038.000000
## .n.Trn.R .n.Tst .n.fit .n.new
## 1421.000000 622.000000 1957.000000 622.000000
## .n.trn err.abs.OOB.mean err.abs.fit.mean err.abs.new.mean
## 2459.000000 3.478161 3.328772 NA
## err.abs.trn.mean
## 3.345564## [1] "Features Importance for selected models:"## All.X..rcv.glmnet.imp
## Hhold.fctrPKn 100.000000
## Q113181.fctrYes 64.984274
## Q115611.fctrYes 52.729697
## Q113181.fctrNo 51.264404
## Q115611.fctrNo 44.707621
## Q98197.fctrNo 40.627886
## Q101163.fctrDad 27.773431
## Hhold.fctrMKy 25.424438
## Q116881.fctrRight 23.579086
## Q106272.fctrYes 22.437747
## Hhold.fctrPKy 17.918579
## Q106997.fctrGr 15.677653
## Q110740.fctrPC 11.933368
## Q99480.fctrNo 6.082982
## Income.fctr.Q 5.630958
## Q98869.fctrNo 5.552206
## Hhold.fctrPKn:.clusterid.fctr2 0.000000
## Hhold.fctrMKy:.clusterid.fctr4 0.000000
## Q108855.fctrYes! 0.000000
## Q106272.fctrNo 0.000000
## Final.All.X..rcv.glmnet.imp
## Hhold.fctrPKn 81.86284
## Q113181.fctrYes 33.28050
## Q115611.fctrYes 100.00000
## Q113181.fctrNo 61.58911
## Q115611.fctrNo 30.25038
## Q98197.fctrNo 62.40403
## Q101163.fctrDad 44.78129
## Hhold.fctrMKy 12.75156
## Q116881.fctrRight 60.37796
## Q106272.fctrYes 0.00000
## Hhold.fctrPKy 21.71103
## Q106997.fctrGr 23.73294
## Q110740.fctrPC 26.95620
## Q99480.fctrNo 28.39881
## Income.fctr.Q 16.36844
## Q98869.fctrNo 43.16389
## Hhold.fctrPKn:.clusterid.fctr2 99.86214
## Hhold.fctrMKy:.clusterid.fctr4 36.43439
## Q108855.fctrYes! 15.06953
## Q106272.fctrNo 13.95534## [1] "glbObsNew prediction stats:"##
## D R
## 209 413## label step_major step_minor label_minor bgn end
## 20 predict.data.new 9 0 0 247.589 259.122
## 21 display.session.info 10 0 0 259.122 NA
## elapsed
## 20 11.533
## 21 NANull Hypothesis (\(\sf{H_{0}}\)): mpg is not impacted by am_fctr.
The variance by am_fctr appears to be independent. #{r q1, cache=FALSE} # print(t.test(subset(cars_df, am_fctr == "automatic")$mpg, # subset(cars_df, am_fctr == "manual")$mpg, # var.equal=FALSE)$conf) # We reject the null hypothesis i.e. we have evidence to conclude that am_fctr impacts mpg (95% confidence). Manual transmission is better for miles per gallon versus automatic transmission.
## label step_major step_minor label_minor bgn
## 14 fit.models 7 0 0 113.283
## 11 cluster.data 4 0 0 12.802
## 12 partition.data.training 5 0 0 61.840
## 15 fit.models 7 1 1 171.205
## 18 fit.data.training 8 0 0 213.910
## 20 predict.data.new 9 0 0 247.589
## 16 fit.models 7 2 2 203.254
## 19 fit.data.training 8 1 1 240.509
## 17 fit.models 7 3 3 210.865
## 13 select.features 6 0 0 110.583
## 1 scrub.data 1 0 0 10.382
## 9 extract.features.end 2 6 6 11.569
## 10 manage.missing.data 3 0 0 12.245
## 8 extract.features.string 2 5 5 11.512
## 2 transform.data 1 1 1 11.299
## 7 extract.features.text 2 4 4 11.467
## 5 extract.features.image 2 2 2 11.399
## 4 extract.features.datetime 2 1 1 11.368
## 6 extract.features.price 2 3 3 11.440
## 3 extract.features 2 0 0 11.352
## end elapsed duration
## 14 171.204 57.922 57.921
## 11 61.839 49.037 49.037
## 12 110.582 48.743 48.742
## 15 203.253 32.048 32.048
## 18 240.508 26.598 26.598
## 20 259.122 11.533 11.533
## 16 210.864 7.610 7.610
## 19 247.589 7.080 7.080
## 17 213.910 3.045 3.045
## 13 113.283 2.700 2.700
## 1 11.298 0.916 0.916
## 9 12.244 0.675 0.675
## 10 12.802 0.557 0.557
## 8 11.568 0.056 0.056
## 2 11.352 0.053 0.053
## 7 11.511 0.045 0.044
## 5 11.440 0.041 0.041
## 4 11.398 0.030 0.030
## 6 11.466 0.026 0.026
## 3 11.368 0.016 0.016
## [1] "Total Elapsed Time: 259.122 secs"
## label step_major step_minor label_minor
## 5 fit.models_0_Low.cor.X 1 4 glmnet
## 4 fit.models_0_Max.cor.Y.rcv.*X* 1 3 glmnet
## 3 fit.models_0_Random 1 2 myrandom_classfr
## 2 fit.models_0_MFO 1 1 myMFO_classfr
## 1 fit.models_0_bgn 1 0 setup
## bgn end elapsed duration
## 5 144.381 171.189 26.809 26.808
## 4 128.246 144.380 16.134 16.134
## 3 120.619 128.245 7.627 7.626
## 2 113.845 120.618 6.773 6.773
## 1 113.809 113.845 0.036 0.036
## [1] "Total Elapsed Time: 171.189 secs"